Category
1,407 papers
This paper audits one such evaluation at the level of individual decision records of a fully local layered defence, CASCADE, a fully local layered defence run in three configurations on a frozen 5,000-sample corpus under a pinned code revision.
A new benchmark to more comprehensively evaluate CUAs'misuse risks, CUAHarm, and explores using LMs to monitor CUAs'actions, finding monitoring unsafe computer-using actions is significantly harder than monitoring conventional unsafe chatbot responses.
Mechanical AutoDAN is introduced, a probe-guided variant of AutoDAN that replaces full-model fitness evaluation with partial forward passes and probe-based scoring inside a genetic prompt search loop, and it is found that refusal is linearly decodable well before the final layer, indicating that safety-relevant behavio...
This work presents Sentinel-RL, an agentic-SOC architecture that decouples topological reasoning from semantic reasoning, and contributes a reusable engineering pattern, a portable HPC deployment pattern, and an enterprise-readiness analysis covering false-positive economics, reversibility guarantees, audit compliance,...
Reach audiences
Advertise in front of researchers, engineers, and readers.
For every coherent and sufficiently expressive finite syntactic system S, we prove the existence of at least one theorem that S cannot produce autonomously. The result is a metatheorem: it proves the existence of a theorem, and applies to every finite syntactic system - security mechanisms, AI systems, formal verifiers...
A patch similarity metric is introduced to detect memorized patches and new patch validation methods are developed that thoroughly evaluate both security and semantic correctness of agent patches for vulnerability patching.
Modern AI agent harnesses expose lifecycle hooks that bind shell commands to runtime events such as session start, tool calls, and file edits. These commands run with host privileges yet ship as lifecycle-hook configuration and may fire at times the LLM never observes. We identify the lifecycle-hook update path, which...
This paper introduces geometric indistinguishability as a conceptual lens for a regime in which privacy-induced dispersion in client updates can make minority-class signals harder for robust aggregation to preserve and suggests that aggregation-aware modeling and sample-aware evaluation are promising directions for tru...
On Agent-SafetyBench, R-Judge, and AgentDojo, federated FGLGuard exceeds the in-domain centralized ceiling on all three benchmarks without pooling any data---where unsupervised anomaly guards and local-only training fail.
This paper proposes GEO Defender, a two-stage defense aligned with the attack chain that requires no fine-tuning of the target LLM's source use at inference, and demonstrates that GEO Defender reduces the average attack success rate, retains 94.12% of benign-evidence use, preserves answer quality, and generalizes to un...
This work introduces Privatehub, which uses contrastive learning within a diffusion model to generate synthetic multi-sensor streams that keep non-private applications detectable while concealing private ones in sensor-intensive environments.
This work proposes a federated inference framework in which several commercial LLM APIs collaborate without requiring access to raw student data or proprietary model internals, and conducts rigorous privacy-utility analysis showing strong privacy guarantees with minimal accuracy loss.
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.
