BlueCodeAgent: A blue teaming agent enabled by automated red teaming for CodeGen AI
BlueCodeAgent is an end-to-end blue-teaming framework built to boost code security using automated red-teaming processes, data, and safety rules to guide LLMs’ defensive decisions. Dynamic testing reduces false positives in vulnerability detection.
Knowledge-Coin Fair Exchange
Fair exchange has been studied in computer science for many decades. The problem consists of enabling two participants to exchange digital information in a way which is fair, even when one may be malicious. The…
RedCodeAgent: Automatic red-teaming agent against diverse code agents
Code agents help streamline software development workflows, but may also introduce critical security risks. Learn how RedCodeAgent automates and improves “red-teaming” attack simulations to help uncover real-world threats that other methods overlook.
IronDict: Transparent Dictionaries from Polynomial Commitments
We present IronDict, a transparent dictionary construction based on polynomial commitment schemes. Transparent dictionaries enable an untrusted server to maintain a mutable dictionary and provably serve clients lookup queries. A major open challenge is supporting…
Lattice-Based Accumulator and Application to Anonymous Credential Revocation
An accumulator is a cryptographic system for compactly representing a set of elements such that every element in the set has a short membership witness. A dynamic accumulator, furthermore, allows elements to be added to…
Efficient Secure Aggregation for Federated Learning
Federated Learning (FL) trains a global model by having each selected device push only its model update to a central server, keeping raw data local. However, those updates can still leak sensitive information unless the server…
Evaluating Privacy Policies under Modern Privacy Laws At Scale: An LLM-Based Automated Approach
Website privacy policies detail an online service’s information practices, including how they handle user data and rights. For many sites, these disclosures are now necessitated by a growing set of privacy regulations, such as GDPR…
Paraphrase Project
The Paraphrase Project addresses a critical and emerging risk: as generative AI and synthetic biology advance, there is a growing possibility that open-source AI tools could be misused to design biological toxins that evade current…