2025 · paper
Protecting Distributed Primitives Against Leakage: Equivocal Secret Sharing and more
The official page lists this work on protecting distributed cryptographic primitives against leakage.[123]
cryptography, proof systems and leakage-resilient protocols
Mor Weiss
מור וייס
Identity: verifiedThe Bar-Ilan faculty page directly identifies Mor Weiss and matches the roster spelling. [123]
Documented foundation
Research & experience
Bar-Ilan computer scientist whose official page focuses on cryptography, proof systems and security for modern computation.[123]
secure multiparty computationzero-knowledge and proof systemsleakage resilienceformat-preserving encryption
CV and official profile
The official faculty page provides education, appointments and selected outputs, but no standalone current CV was verified.[123]
Selected work
Representative records, not a complete publication list. Metadata confirms attribution; it does not independently replicate a result.
Patent evidence
1 catalogued patent record · family unassigned for 1 record
Coverage: Partial inventor search
First-party patent list and expanded inventor-name discovery returned the already-preserved IBM complex format-preserving encryption invention. US9634838B2 and its publication variant US20150358159A1 were intentionally not added again. No further distinct attributable invention was verified; this is not an exhaustive portfolio claim.
Complex format-preserving encryption scheme
US9634838B2
Original report record
Preserved from the original report; see its cited evidence and limitations.[124][125]
Original report snapshot
Original evidence: verified record
The first-party patent list and opened patent record attribute this IBM-assigned US patent to Mor Weiss and Boris Rozenberg; legal scope and current enforceability were not assessed.[124][125]
Records are counted separately from identified families. Author-reported entries are labelled and may still need publication verification. Inventorship, publication-time applicant and current ownership are different facts. No legal-status, patentability or freedom-to-operate conclusion is made.
Scores prioritize research fit from 1–10; they are not probabilities.
Review: Reviewed with limitations
Proposed capability matches, not confirmed relationships. Scores are analyst judgments with low forecast confidence; researcher interests, capacity and feasibility need confirmation.
Internal connections
12 candidates
Connection 1
Ran Gelles
Proposal hypothesis: Gelles's noise-resilient interactive protocols and Mor Weiss's secure distributed computation can test whether reliability measures preserve the intended security statement.[57][58][123]
First test and score details
First test
Proposed first test: Specify a toy secure two-party exchange over a corrupted channel and compare completion rate, transcript exposure and overhead with a noiseless reference.
Score components
- complementarity
- 3
- feasible first test
- 3
- topic overlap
- 3
Why this rank
Rank 1/12; fit 9/10: topic overlap 3/4, complementarity 3/3, first-test feasibility 3/3. Added capability match outside the original initiative graph; prior collaboration or novelty was not established. Equal scores retain originals first, then stable profile order. The underlying capabilities and proposed first test explain the component judgments. Specific scientific limitation: Channel noise and malicious behavior require separate assumptions; error correction is not encryption.
Conditions
Analyst proposal hypothesis, not an established collaboration, commitment, evidence-confidence rating or assessment of researcher quality; confirm participation and access before work.
Connection 2
Shahar Somin
Proposal hypothesis: Somin's temporal fingerprinting identifies a concrete leakage risk for Mor Weiss's secure distributed protocols.[64][65][123]
First test and score details
First test
Proposed first test: Generate synthetic encrypted-message timings and compare coordination inference before and after a specified padding schedule, reporting leakage and overhead.
Score components
- complementarity
- 3
- feasible first test
- 3
- topic overlap
- 3
Why this rank
Rank 2/12; fit 9/10: topic overlap 3/4, complementarity 3/3, first-test feasibility 3/3. Added capability match outside the original initiative graph; prior collaboration or novelty was not established. Equal scores retain originals first, then stable profile order. The underlying capabilities and proposed first test explain the component judgments. Specific scientific limitation: Encryption alone does not hide metadata; no real-person identity matching is proposed.
Conditions
Analyst proposal hypothesis, not an established collaboration, commitment, evidence-confidence rating or assessment of researcher quality; confirm participation and access before work.
Connection 3
Amir Leshem
Proposal hypothesis: Leshem can define an adversarial federated-update problem and Mor Weiss can test private verification of a limited update property.[111][112][123]
First test and score details
First test
Proposed first test: Compare a toy proof of update-bound compliance with plaintext inspection on verification cost and accepted invalid updates.
Score components
- complementarity
- 3
- feasible first test
- 2
- topic overlap
- 3
Why this rank
Rank 3/12; fit 8/10: topic overlap 3/4, complementarity 3/3, first-test feasibility 2/3. Added capability match outside the original initiative graph; prior collaboration or novelty was not established. Independent review lowered feasibility by one point: The update-bound proof test has essentially the same unresolved proof-statement/security assumptions as Ethan Fetaya-Mor Weiss, which receives feasibility 2/3. Name the committed update, bounded predicate, adversary and concrete proof implementation, or apply the same 2/3 feasibility here. Equal scores retain originals first, then stable profile order. The underlying capabilities and proposed first test explain the component judgments. Specific scientific limitation: A proven update bound does not establish that training data or model updates are benign.
Conditions
Analyst proposal hypothesis, not an established collaboration, commitment, evidence-confidence rating or assessment of researcher quality; confirm participation and access before work.
Show 9 moreShow fewer internal connections
Connection 4
Ilan Reuven Cohen
Proposal hypothesis: Ilan Cohen can specify a fair allocation rule and Mor Weiss can examine whether its execution can be verified on private bids or constraints.[119][120][123]
First test and score details
First test
Proposed first test: Encode a small allocation rule on synthetic inputs and compare proof cost with direct recomputation and disclosed-input volume.
Score components
- complementarity
- 3
- feasible first test
- 2
- topic overlap
- 3
Why this rank
Rank 4/12; fit 8/10: topic overlap 3/4, complementarity 3/3, first-test feasibility 2/3. Added capability match outside the original initiative graph; prior collaboration or novelty was not established. Independent review lowered feasibility by one point: The allocation proof proposal leaves the rule, protected inputs and public statement unspecified. Other private-execution pairs use feasibility 2/3. Name a fixed small rule and leakage/security assumptions before maximum feasibility; otherwise use 2/3. Equal scores retain originals first, then stable profile order. The underlying capabilities and proposed first test explain the component judgments. Specific scientific limitation: Proofs establish rule execution, not that the chosen fairness rule is normatively appropriate.
Conditions
Analyst proposal hypothesis, not an established collaboration, commitment, evidence-confidence rating or assessment of researcher quality; confirm participation and access before work.
Connection 5
Ethan Fetaya
Original proposal
Proposal hypothesis: Fetaya can define a federated-learning update constraint and Mor Weiss can formalize how to prove compliance without revealing client examples.[73][123]
First test and score details
First test
Proposed first test: For a toy update-norm constraint, compare a proof-based audit with plaintext checking on proof overhead and accepted malicious updates.
Score components
- complementarity
- 3
- feasible first test
- 2
- topic overlap
- 2
Why this rank
Rank 5/12; fit 7/10: topic overlap 2/4, complementarity 3/3, first-test feasibility 2/3. Original initiative connection retained. New candidate Ran Gelles ranks higher at 9/10 (overlap 3, complementarity 3, feasibility 3). Its proposed capability split: Proposal hypothesis: Gelles's noise-resilient interactive protocols and Mor Weiss's secure distributed computation can test whether reliability measures preserve the intended security statement. Compare the cited first experiments; these are analyst priorities, not measured success rates. Equal scores retain originals first, then stable profile order. The underlying capabilities and proposed first test explain the component judgments. Specific scientific limitation: Norm compliance is not benign model behaviour; a security model is needed before claiming protection.
Conditions
Analyst proposal hypothesis, not an established collaboration, commitment, evidence-confidence rating or assessment of researcher quality; confirm participation and access before work. Original initiative conditions remain: o01 Mor Weiss: Conditional later role: only after a protected-input threat model exists, specify a computation or access-policy statement that can be proven without revealing inputs.
Connection 6
Gonen Singer
Proposal hypothesis: Singer can specify a resource-allocation calculation and Mor Weiss can test a protocol that executes it without revealing individual inputs.[79][80][123]
First test and score details
First test
Proposed first test: Compare a toy private aggregate allocation with plaintext computation on output equality, communication and leakage assumptions.
Score components
- complementarity
- 3
- feasible first test
- 2
- topic overlap
- 2
Why this rank
Rank 6/12; fit 7/10: topic overlap 2/4, complementarity 3/3, first-test feasibility 2/3. Added capability match outside the original initiative graph; prior collaboration or novelty was not established. Equal scores retain originals first, then stable profile order. The underlying capabilities and proposed first test explain the component judgments. Specific scientific limitation: Privacy of execution does not validate the allocation objective or prevent inference from outputs.
Conditions
Analyst proposal hypothesis, not an established collaboration, commitment, evidence-confidence rating or assessment of researcher quality; confirm participation and access before work.
Connection 7
Izack Cohen
Proposal hypothesis: Izack Cohen can define a process statistic needed for queue management and Mor Weiss can examine privacy-preserving computation of that statistic.[97][98][123]
First test and score details
First test
Proposed first test: Compute aggregate queue occupancy from synthetic distributed logs and compare secure and plaintext methods on equality, overhead and information exposure.
Score components
- complementarity
- 3
- feasible first test
- 2
- topic overlap
- 2
Why this rank
Rank 7/12; fit 7/10: topic overlap 2/4, complementarity 3/3, first-test feasibility 2/3. Added capability match outside the original initiative graph; prior collaboration or novelty was not established. Equal scores retain originals first, then stable profile order. The underlying capabilities and proposed first test explain the component judgments. Specific scientific limitation: Access governance and output leakage remain outside a simple cryptographic benchmark.
Conditions
Analyst proposal hypothesis, not an established collaboration, commitment, evidence-confidence rating or assessment of researcher quality; confirm participation and access before work.
Connection 8
Moti Medina
Proposal hypothesis: Medina can model faulty computation or network components while Mor Weiss specifies what a secure protocol should reveal during recovery.[100][123]
First test and score details
First test
Proposed first test: Construct a toy recovery transcript and compare leakage and completion under two failover designs in an explicit threat model.
Score components
- complementarity
- 3
- feasible first test
- 2
- topic overlap
- 2
Why this rank
Rank 8/12; fit 7/10: topic overlap 2/4, complementarity 3/3, first-test feasibility 2/3. Added capability match outside the original initiative graph; prior collaboration or novelty was not established. Equal scores retain originals first, then stable profile order. The underlying capabilities and proposed first test explain the component judgments. Specific scientific limitation: Fault tolerance alone does not preserve secrecy or active security.
Conditions
Analyst proposal hypothesis, not an established collaboration, commitment, evidence-confidence rating or assessment of researcher quality; confirm participation and access before work.
Connection 9
Yair Noam
Proposal hypothesis: Noam can define the minimum information needed for cooperative spectrum estimation and Mor Weiss can examine a private exchange protocol.[123][130][131]
First test and score details
First test
Proposed first test: Use synthetic spectrum observations to compare plaintext and secure aggregate estimation on error, communication and leakage assumptions.
Score components
- complementarity
- 3
- feasible first test
- 2
- topic overlap
- 2
Why this rank
Rank 9/12; fit 7/10: topic overlap 2/4, complementarity 3/3, first-test feasibility 2/3. Added capability match outside the original initiative graph; prior collaboration or novelty was not established. Equal scores retain originals first, then stable profile order. The underlying capabilities and proposed first test explain the component judgments. Specific scientific limitation: Cryptographic overhead and the exact adversary may make a private protocol impractical.
Conditions
Analyst proposal hypothesis, not an established collaboration, commitment, evidence-confidence rating or assessment of researcher quality; confirm participation and access before work.
Connection 10
Hila Chalutz-Ben Gal
Original proposal
Proposal hypothesis: Chalutz-Ben Gal can define a narrowly justified workforce statistic and Mor Weiss can assess a protocol that reveals the statistic without revealing individual records.[22][23][123]
First test and score details
First test
Proposed first test: On synthetic skill counts, formalize one aggregate query and compare data exposure and computation cost with releasing row-level records.
Score components
- complementarity
- 3
- feasible first test
- 2
- topic overlap
- 1
Why this rank
Rank 10/12; fit 6/10: topic overlap 1/4, complementarity 3/3, first-test feasibility 2/3. Original initiative connection retained. New candidate Ran Gelles ranks higher at 9/10 (overlap 3, complementarity 3, feasibility 3). Its proposed capability split: Proposal hypothesis: Gelles's noise-resilient interactive protocols and Mor Weiss's secure distributed computation can test whether reliability measures preserve the intended security statement. Compare the cited first experiments; these are analyst priorities, not measured success rates. Equal scores retain originals first, then stable profile order. The underlying capabilities and proposed first test explain the component judgments. Specific scientific limitation: Consent, purpose limitation and a leakage model are prerequisites; cryptography alone does not make personnel analytics acceptable.
Conditions
Analyst proposal hypothesis, not an established collaboration, commitment, evidence-confidence rating or assessment of researcher quality; confirm participation and access before work. Original initiative conditions remain: o01 Mor Weiss: Conditional later role: only after a protected-input threat model exists, specify a computation or access-policy statement that can be proven without revealing inputs. o01 Hila Chalutz-Ben Gal: Conditional later role: design a separately approved researcher-use study of noticing and correcting unsupported recommendations.
Connection 11
Jacob Goldberger
Original proposal
Proposal hypothesis: Goldberger can define an uncertainty-based triage calculation and Mor Weiss can examine private verification of that calculation, leaving empirical calibration to a separate evaluation.[75][76][123]
First test and score details
First test
Proposed first test: Encode a small threshold-based triage rule over synthetic uncertainty values and measure proof/verifier cost relative to direct evaluation.
Score components
- complementarity
- 3
- feasible first test
- 2
- topic overlap
- 1
Why this rank
Rank 11/12; fit 6/10: topic overlap 1/4, complementarity 3/3, first-test feasibility 2/3. Original initiative connection retained. New candidate Ran Gelles ranks higher at 9/10 (overlap 3, complementarity 3, feasibility 3). Its proposed capability split: Proposal hypothesis: Gelles's noise-resilient interactive protocols and Mor Weiss's secure distributed computation can test whether reliability measures preserve the intended security statement. Compare the cited first experiments; these are analyst priorities, not measured success rates. Equal scores retain originals first, then stable profile order. The underlying capabilities and proposed first test explain the component judgments. Specific scientific limitation: Cryptographic correctness cannot certify calibration or diagnostic validity, so the original connection remains exploratory.
Conditions
Analyst proposal hypothesis, not an established collaboration, commitment, evidence-confidence rating or assessment of researcher quality; confirm participation and access before work. Original initiative conditions remain: o01 Mor Weiss: Conditional later role: only after a protected-input threat model exists, specify a computation or access-policy statement that can be proven without revealing inputs.
Connection 12
Ori Ernst
Original proposal
Proposal hypothesis: Ernst can specify a source-alignment computation and Mor Weiss can ask whether its execution can be proven without exposing protected inputs; a proof would not establish scientific truth.[93][94][95][123]
First test and score details
First test
Proposed first test: Specify a toy statement that each released sentence maps to an allowed source index; benchmark proof size and verification cost on synthetic inputs.
Score components
- complementarity
- 3
- feasible first test
- 2
- topic overlap
- 1
Why this rank
Rank 12/12; fit 6/10: topic overlap 1/4, complementarity 3/3, first-test feasibility 2/3. Original initiative connection retained. New candidate Ran Gelles ranks higher at 9/10 (overlap 3, complementarity 3, feasibility 3). Its proposed capability split: Proposal hypothesis: Gelles's noise-resilient interactive protocols and Mor Weiss's secure distributed computation can test whether reliability measures preserve the intended security statement. Compare the cited first experiments; these are analyst priorities, not measured success rates. Equal scores retain originals first, then stable profile order. The underlying capabilities and proposed first test explain the component judgments. Specific scientific limitation: The original later-stage role needs a protected-input threat model and a tractable proof statement before implementation.
Conditions
Analyst proposal hypothesis, not an established collaboration, commitment, evidence-confidence rating or assessment of researcher quality; confirm participation and access before work. Original initiative conditions remain: o01 Mor Weiss: Conditional later role: only after a protected-input threat model exists, specify a computation or access-policy statement that can be proven without revealing inputs.
External connections
10 candidates
Connection 1
Yevgeniy Dodis
New York University
Proposed capability match: Mor Weiss's secure multiparty computation, zero-knowledge and proof systems can be paired with Yevgeniy Dodis's documented leakage-resilient cryptography, randomness extraction for leakage-resilient proofs for privacy-preserving ai audits. The specific contribution is explicit leakage models and randomness; this transfer is an analyst hypothesis.[123][449]
First test and score details
First test
Sweep a bounded leakage model on a toy distributed primitive and test random-seed reuse as an adversarial case using a toy privacy-preserving AI-audit or distributed-proof task with explicit allowed leakage. Compare key/secret distinguishability and the stated leakage bound with a non-private auditable computation and a standard secure baseline.
Score components
- complementarity
- 3
- feasible first test
- 3
- topic overlap
- 4
Why this rank
Rank 1/10 after semantic revision; analyst score 10 = max(1, 4+3+3): topic overlap 4/4, complementarity 3/3, feasible first test 3/3. A bounded offline comparison is specified; required datasets and domain assumptions must still be checked.
Conditions
Proposed fit, not an assertion of a new or active relationship. Independent review pending; forecast confidence low. Partner interest, capacity, data access and any required experimental approvals/resources are unverified.
Connection 2
Yael Kalai
Massachusetts Institute of Technology
Proposed capability match: Mor Weiss's secure multiparty computation, zero-knowledge and proof systems can be paired with Yael Kalai's documented zero-knowledge proofs, verification of computation for leakage-resilient proofs for privacy-preserving ai audits. The specific contribution is verification with corrupted interaction; this transfer is an analyst hypothesis.[123][465]
First test and score details
First test
Compare verification protocols on a tiny computation while corrupting messages or intermediate answers using a toy privacy-preserving AI-audit or distributed-proof task with explicit allowed leakage. Compare soundness, round complexity and tolerance to corrupted interaction with a non-private auditable computation and a standard secure baseline.
Score components
- complementarity
- 3
- feasible first test
- 3
- topic overlap
- 4
Why this rank
Rank 2/10 after semantic revision; analyst score 10 = max(1, 4+3+3): topic overlap 4/4, complementarity 3/3, feasible first test 3/3. A bounded offline comparison is specified; required datasets and domain assumptions must still be checked.
Conditions
Proposed fit, not an assertion of a new or active relationship. Independent review pending; forecast confidence low. Partner interest, capacity, data access and any required experimental approvals/resources are unverified.
Connection 3
Shafi Goldwasser
Massachusetts Institute of Technology
Original proposal
MIT documents Goldwasser's cryptography and security leadership, offering complementary depth for proof-system and adversarial-model review; no willingness or relationship is asserted.[123][126][457]
First test and score details
First test
Specify one toy audit statement: a committed vector's coordinates lie within a public bound, with an explicitly stated verifier view and permitted leakage. Enumerate completeness, soundness and privacy obligations and check a small reference transcript plus malformed examples. Select a suitable existing proof primitive only after this specification; a new security proof and optimized implementation are later stages.
Score components
- complementarity
- 3
- feasible first test
- 2
- topic overlap
- 4
Why this rank
Rank 3/10 after semantic revision; analyst score 9 = max(1, 4+3+2): topic overlap 4/4, complementarity 3/3, feasible first test 2/3. Auditability and cryptography are a direct fit, but a bounded statement/threat-model exercise precedes a security proof or implementation benchmark. A bounded offline comparison is specified; required datasets and domain assumptions must still be checked. Original retained exactly at rank 3; preceding alternatives are Yevgeniy Dodis (10; 4+3+3), Yael Kalai (10; 4+3+3). Its first stage now has explicit unconfirmed platform, protocol or interface prerequisites; higher totals reflect the other scoped tests, not comparative researcher quality.
Conditions
Proposed fit, not an assertion of a new or active relationship. Independent review pending; forecast confidence low. Partner interest, capacity, data access and any required experimental approvals/resources are unverified. Post-review scope: Auditability and cryptography are a direct fit, but a bounded statement/threat-model exercise precedes a security proof or implementation benchmark. This revised proposal awaits independent targeted re-review; simulated outcomes would establish model behavior only, not biological, clinical or deployed benefit.
Show 7 moreShow fewer external connections
Connection 4
Dan Boneh
Stanford University
Proposed capability match: Mor Weiss's secure multiparty computation, zero-knowledge and proof systems can be paired with Dan Boneh's documented applied cryptography, computer security for leakage-resilient proofs for privacy-preserving ai audits. The specific contribution is applied cryptographic protocol engineering; this transfer is an analyst hypothesis.[123][439]
First test and score details
First test
Prototype a minimal signed or encrypted audit exchange and enumerate adversarial replays and malformed inputs using a toy privacy-preserving AI-audit or distributed-proof task with explicit allowed leakage. Compare forgery/replay rejection and protocol overhead with a non-private auditable computation and a standard secure baseline.
Score components
- complementarity
- 3
- feasible first test
- 3
- topic overlap
- 3
Why this rank
Rank 4/10 after semantic revision; analyst score 9 = max(1, 3+3+3): topic overlap 3/4, complementarity 3/3, feasible first test 3/3. A bounded offline comparison is specified; required datasets and domain assumptions must still be checked.
Conditions
Proposed fit, not an assertion of a new or active relationship. Independent review pending; forecast confidence low. Partner interest, capacity, data access and any required experimental approvals/resources are unverified.
Connection 5
Zvika Brakerski
Weizmann Institute of Science
Proposed capability match: Mor Weiss's secure multiparty computation, zero-knowledge and proof systems can be paired with Zvika Brakerski's documented fully homomorphic encryption, quantum cryptography for leakage-resilient proofs for privacy-preserving ai audits. The specific contribution is encrypted and quantum-aware computation; this transfer is an analyst hypothesis.[123][441]
First test and score details
First test
Compare toy threshold encrypted evaluation or quantum-error accounting with an unprotected baseline after fixing assumptions using a toy privacy-preserving AI-audit or distributed-proof task with explicit allowed leakage. Compare correctness, communication overhead and sensitivity to noise with a non-private auditable computation and a standard secure baseline.
Score components
- complementarity
- 3
- feasible first test
- 3
- topic overlap
- 3
Why this rank
Rank 5/10 after semantic revision; analyst score 9 = max(1, 3+3+3): topic overlap 3/4, complementarity 3/3, feasible first test 3/3. A bounded offline comparison is specified; required datasets and domain assumptions must still be checked.
Conditions
Proposed fit, not an assertion of a new or active relationship. Independent review pending; forecast confidence low. Partner interest, capacity, data access and any required experimental approvals/resources are unverified.
Connection 6
Srini Devadas
Massachusetts Institute of Technology
Proposed capability match: Mor Weiss's secure multiparty computation, zero-knowledge and proof systems can be paired with Srini Devadas's documented secure computer architecture, homomorphic-encryption accelerators for leakage-resilient proofs for privacy-preserving ai audits. The specific contribution is hardware execution of privacy-preserving primitives; this transfer is an analyst hypothesis.[123][448]
First test and score details
First test
Replay a small encrypted-compute or proof-verification kernel under alternative memory and accelerator assumptions using a toy privacy-preserving AI-audit or distributed-proof task with explicit allowed leakage. Compare runtime, memory traffic and explicitly stated leakage exposure with a non-private auditable computation and a standard secure baseline.
Score components
- complementarity
- 3
- feasible first test
- 3
- topic overlap
- 3
Why this rank
Rank 6/10 after semantic revision; analyst score 9 = max(1, 3+3+3): topic overlap 3/4, complementarity 3/3, feasible first test 3/3. A bounded offline comparison is specified; required datasets and domain assumptions must still be checked.
Conditions
Proposed fit, not an assertion of a new or active relationship. Independent review pending; forecast confidence low. Partner interest, capacity, data access and any required experimental approvals/resources are unverified.
Connection 7
Anna Lysyanskaya
Brown University
Proposed capability match: Mor Weiss's secure multiparty computation, zero-knowledge and proof systems can be paired with Anna Lysyanskaya's documented privacy-enhancing cryptography, cryptographic foundations for leakage-resilient proofs for privacy-preserving ai audits. The specific contribution is privacy-minimizing disclosures; this transfer is an analyst hypothesis.[123][471]
First test and score details
First test
Design a toy attribute-disclosure audit that reveals only a required predicate and compare it with full-record disclosure using a toy privacy-preserving AI-audit or distributed-proof task with explicit allowed leakage. Compare linkability, information disclosed and verification cost with a non-private auditable computation and a standard secure baseline.
Score components
- complementarity
- 3
- feasible first test
- 3
- topic overlap
- 3
Why this rank
Rank 7/10 after semantic revision; analyst score 9 = max(1, 3+3+3): topic overlap 3/4, complementarity 3/3, feasible first test 3/3. A bounded offline comparison is specified; required datasets and domain assumptions must still be checked.
Conditions
Proposed fit, not an assertion of a new or active relationship. Independent review pending; forecast confidence low. Partner interest, capacity, data access and any required experimental approvals/resources are unverified.
Connection 8
Silvio Micali
Massachusetts Institute of Technology
Proposed capability match: Mor Weiss's secure multiparty computation, zero-knowledge and proof systems can be paired with Silvio Micali's documented cryptography, secure protocols for leakage-resilient proofs for privacy-preserving ai audits. The specific contribution is cryptographic protocol and proof design; this transfer is an analyst hypothesis.[123][475]
First test and score details
First test
Specify a minimal privacy-preserving audit protocol and test its completeness and soundness on adversarial toy transcripts using a toy privacy-preserving AI-audit or distributed-proof task with explicit allowed leakage. Compare verification cost and counterexamples to claimed soundness with a non-private auditable computation and a standard secure baseline.
Score components
- complementarity
- 2
- feasible first test
- 3
- topic overlap
- 3
Why this rank
Rank 8/10 after semantic revision; analyst score 8 = max(1, 3+2+3): topic overlap 3/4, complementarity 2/3, feasible first test 3/3. A bounded offline comparison is specified; required datasets and domain assumptions must still be checked.
Conditions
Proposed fit, not an assertion of a new or active relationship. Independent review pending; forecast confidence low. Partner interest, capacity, data access and any required experimental approvals/resources are unverified. The inspected MIT group roster labels this appointment professor post-tenure.
Connection 9
Ronald L. Rivest
Massachusetts Institute of Technology
Proposed capability match: Mor Weiss's secure multiparty computation, zero-knowledge and proof systems can be paired with Ronald L. Rivest's documented cryptography, computer and network security for leakage-resilient proofs for privacy-preserving ai audits. The specific contribution is auditable integrity and algorithmic security; this transfer is an analyst hypothesis.[123][489]
First test and score details
First test
Construct a small independently checkable audit log with an explicit tampering and selective-disclosure test using a toy privacy-preserving AI-audit or distributed-proof task with explicit allowed leakage. Compare undetected alteration rate and audit cost with a non-private auditable computation and a standard secure baseline.
Score components
- complementarity
- 2
- feasible first test
- 3
- topic overlap
- 3
Why this rank
Rank 9/10 after semantic revision; analyst score 8 = max(1, 3+2+3): topic overlap 3/4, complementarity 2/3, feasible first test 3/3. A bounded offline comparison is specified; required datasets and domain assumptions must still be checked.
Conditions
Proposed fit, not an assertion of a new or active relationship. Independent review pending; forecast confidence low. Partner interest, capacity, data access and any required experimental approvals/resources are unverified. The inspected MIT group roster labels this appointment professor post-tenure.
Connection 10
Vinod Vaikuntanathan
Massachusetts Institute of Technology
Proposed capability match: Mor Weiss's leakage-resilient protocols and proof systems can be paired with Vinod Vaikuntanathan's documented cryptography role to examine private computation for AI auditing. The homomorphic-encryption implementation is a proposed method requiring finer-grained source confirmation.[123][498]
First test and score details
First test
Implement a toy arithmetic task under a standard homomorphic-encryption baseline and make trust assumptions explicit using a toy privacy-preserving AI-audit or distributed-proof task with explicit allowed leakage. Compare ciphertext growth, runtime and plaintext-equivalent correctness with a non-private auditable computation and a standard secure baseline.
Score components
- complementarity
- 2
- feasible first test
- 3
- topic overlap
- 3
Why this rank
Rank 10/10 after semantic revision; analyst score 8 = max(1, 3+2+3): topic overlap 3/4, complementarity 2/3, feasible first test 3/3. Broad cryptography overlap is documented; complementarity is limited until the specific encrypted-computation method is independently checked. The toy protocol is an offline first test.
Conditions
Proposed fit, not an assertion of a new or active relationship. Independent review pending; forecast confidence low. Partner interest, capacity, data access and any required experimental approvals/resources are unverified. Retained current evidence is a broad cryptography biography; exact homomorphic-encryption method expertise requires source review.
Evidence & open questions
- No standalone CV was verified.
- Patent legal status, family scope and ownership beyond the opened record were not analyzed.
Inspect claim ratings and independent review
Mor Weiss researches cryptography and proof systems, including leakage-protected distributed primitives, and is named on US9634838B2. [123][124][125]
High confidenceReview: reviewedPatent family scope, legal status and current ownership were not analyzed.
Review record
- root: supports. The Hebrew BIU profile lists cryptography and proof systems. Its patent page links the exact record; US9634838B2 names Mor Weiss and Boris Rozenberg. No legal status or current ownership conclusion is drawn.
Leakage-resilient proofs for privacy-preserving AI audits are a future research hypothesis grounded in Weiss's methods and Goldwasser's cryptography expertise. [123][126]
Low confidenceReview: reviewedComposability, implementation leakage and operational value have not been tested.
Review record
- root: supports. Weiss’s proof-system work and Goldwasser’s MIT cryptography/security affiliation support a possible research pairing. The proposed AI-audit proof and its feasibility remain to be designed.