Category
1,407 papers
Proxy Manifold Alignment (PMA), a novel attack against E2EO in privacy-preserving LLMs, which employs Word2Vec to model the co-occurrence patterns within the obfuscated stream and the public corpus independently, and constructs two proxy vector embeddings.
Aligned language models fail under two independent pressures: the structural jailbreak class recently formalized as Involuntary In-Context Learning (IICL), which reframes a harmful request as the final missing cell of a data-labeling task completed by pattern rather than judged as content; and the erosion of safety ali...
A privacy-preserving federated learning framework for clinical EEG data that uses masking-based secure aggregation as its core protection mechanism that remains compatible with federated model training, although malicious-setting safeguards and lightweight consistency-checking mechanisms introduce additional computatio...
Recent cryptographic results establish that neural networks can be backdoored such that no efficient algorithm can distinguish them from a clean model. These guarantees, however, have been confined to stylised architectures of limited practical relevance, leaving open whether comparable undetectability extends to moder...
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work proposes a novel formalization of label flipping attacks as a per-round constrained optimization problem, derives a greedy label-selection rule for logistic regression, and empirically evaluates it beyond its derivation setting, including on MLPs and robust aggregators.
Tempora-Fusion is presented, the first homomorphic TLP scheme with efficient public verification of both individual puzzle solutions and homomorphic linear combinations, and formalize verifiable homomorphic linear-combination TLPs, prove privacy and solution validity in this model.
This work establishes conditional false-accusation bounds for arbitrary recovered bit patterns, a finite completeness bound under a hidden-bias residual channel, and a deterministic tracing-score bound for correlated feature-distillation errors to support verifiable tracing under explicit statistical and cryptographic...
The results show that colluding semi-honest nodes can recover the original local updates of honest nodes, enabling downstream reconstruction of private training data, and demonstrate that SA alone does not guarantee privacy in DFL when local aggregation induces asymmetric observations.
We introduce HoneyRoute, an inference-serving layer that detects whether an incoming request is malicious and, if so, routes it to a dedicated honeypot model, shielding production while the adversary's interaction is continuously harvested for intelligence. Existing defenses embed traps inside model memory or rebuild d...
DRIFT, a black-box attack that combines partial forward diffusion with stochastic reverse resampling, achieves 98-100% attack success and the best image quality among the compared attacks, without secret keys, verifier internals, or per-image gradient optimization.
VEX-Bench is introduced, the first benchmark for evaluating LLM agents'ability to assess the exploitability of software supply chain vulnerabilities, and contains 75 real-world cases mined from GitHub and labeled by security experts, covering Python, Java, and Go.
It is argued that the operational unit of defence should be a revisable coordination episode linking observed transfers, task authority, and response history, and it makes the recommendation to monitor across executions testable without claiming a new detector or a measured containment benefit.
Research Manager Mike Walker reflects on a career spanning hacker culture, cybersecurity, and AI, sharing lessons about trust, teamwork, leadership, and why solving difficult problems requires curiosity, judgment, agility—and an understanding of the rules. The post Learn the rules: The hacker mindset appeared first on Microsoft Research.
GPT-Lab
· gpt-lab.eu
Oct 30, 2026
Critical flaws, compromised release channels and agentic AI threats landed within days of each other in mid-October 2026. Why “Black October” may say more about how well we now find weaknesses than about the attacks themselves. The post Black October? The Week AI Changed the Cybersecurity Conversation appeared first on GPT-Lab.
Gemini 4 Carbon is our strongest model with state-of-the-art cybersecurity and long horizon capabilities.
Gemini 3.8 Flash and 3.8 Flash Cyber deliver next-generation intelligence for agentic workflows and cybersecurity.
Google introduces Gemini 3.5 Flash Cyber, a lightweight cybersecurity model to find and patch vulnerabilities.
Students from the MIT Cybersecurity Clinic help local governments and other vulnerable organizations defend against digital threats.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
