Category
1,407 papers
DirBucket is the only method that consistently achieves strong target detection with no non-target activation, detecting non-compliance in every audit within 23 audited answers on the authors' primary benchmark, and the results suggest that embedding-space watermarking can make document reuse in third-party RAG statist...
The findings support selfie-capture motion as a low-friction auxiliary signal, while leaving cross-device, cross-session, and real injection-attack evaluation as necessary next steps.
On-policy RL preserves a safety buffer inherent in the model's own generation distribution, one that is bypassed during off-policy settings, one that is bypassed during off-policy settings.
Stateless Bernoulli Watermarking (SBW) is introduced, a new statistical watermark for Large Language Models that determines green list membership through independent per-token Bernoulli trials, reducing membership complexity to $O(1)$ and enabling single-kernel execution with zero intermediate allocations.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Spruce learns compact binary codes that preserve candidates for full-precision reranking, replacing corpus-wide embedding scoring with efficient Hamming-distance computation under two-server multi-party computation under two-server multi-party computation (MPC).
CRAW is introduced, a codec-robust audio watermarking framework that jointly improves robustness against neural re-synthesis while maintaining high perceptual quality and achieves state-of-the-art robustness against neural codecs, denoisers, and vocoders.
A federated learning framework that combines a Gaussian-mechanism differential privacy layer with a coordinate-wise trimmed-mean Byzantine-robust aggregation rule, evaluated on a simulated cross-institutional classification task resembling fraud and clinical-risk scoring.
A deployed system that scores an address by its position in a multi-chain transaction graph rather than by its presence in a list, and an adversarial harness of eight recurrent reinforcement-learned archetypes that passes an 8-criterion degeneracy audit and exposes a measured blind spot of the deployed heads against sy...
As vehicular networks move toward 5G/6G edge intelligence, federated learning (FL) is widely promoted as a privacy-preserving way for vehicles and infrastructure to train shared models without exposing raw sensor data. Yet the updates clients transmit still leak enough information to identify who sent them, which threa...
This work studies refusal directions through the training dynamics across refusal datasets and reveals that their brittleness is associated with repetitive refusal starts, which is linked to concentration of gradients and refusal features in a low-dimensional subspace.
This paper proposes a novel technique for accurately and automatically inferring LLM-related scrapers and demonstrates that the approach can reliably identify which scrapers feed which LLM, including several that are not publicly known or disclosed by the companies.
The results show that context-aware security assessment is a practical complement to existing AE processes and can support safer and more responsible research artifact sharing.
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.
