Category
1,407 papers
The misaligned AI behaviors that led to the OpenAI-Hugging Face incident are identified and it is shown that an auditing agent can elicit similar behaviors given high-level qualitative descriptions and that RL is a promising direction to do so.
DECEIVE (Deepfake Exploitation of Cognitive Engagement and Implicit Visual Evaluation), a framework that models how deepfake videos are validated as adversarial payloads through behavioral and neuro-physiological screening of viewers, and how attacks can be refined by selecting payloads that evade detection.
This paper presents AuditBench, a new benchmark dataset for evaluating the capabilities of LLMs at investigating security-related system audit logs. We design and use this benchmark to explore the performance of LLMs on four log-investigation tasks that incident response teams commonly perform, ranging from triaging al...
D-STT, a simple yet effective defense algorithm that identifies and explicitly decodes safety trigger tokens of the given safety-aligned LLM to activate the model's learned safety patterns, effectively preserves model usability by introducing minimum intervention in the decoding process.
Reach audiences
Advertise in front of researchers, engineers, and readers.
A per-token logits mask is applied that deterministically eliminates single-query column-use violations on the supported SQL fragment in a single decoding pass and achieves 0% Leakage Rate and Coverage up to 88.7% on Spider-CU, while staying within +10% tokens of direct prompting.
As Large Language Models (LLMs) are increasingly deployed in cross-linguistic contexts, ensuring safety across diverse regulatory and cultural environments has become a critical challenge. However, existing multilingual benchmarks largely rely on general risk taxonomies and machine-translated data, limiting evaluation...
Anyone with a public footprint leaks facts that were never stated, and language models make the inference cheap. We present a framework for measuring and reducing this inference exposure that runs on the owner's own CPU with no language model at analysis time, instantiated on organisations and on individuals. It starts...
When a language-model audit finds no leak, what is needed to certify non-leakage? We study guarantees over a declared prompt domain under an executable leakage criterion and decoding rule. For general bounded polynomial-time evaluators, a supplied leaking execution is polynomial-time checkable, while leak existence is...
The research indicates that AI governance responsibilities are often embedded within existing privacy roles, contributing to the rise of hybrid positions alongside dedicated AI governance roles.
Benign-Anchored Ranking and Selection (BARS), a two-stage filter that replaces CMD's global anchor with the benign-class mean and applies an order-preserving decorrelation step, is proposed, which reduces false alarms by up to 32% while maintaining similar detection rates, with larger gains under stronger imbalance.
The dithered Gaussian mechanism is presented, an alternative to the discrete Gaussian mechanism for differential privacy that discretizes the private output rather than the noise distribution itself, and it is shown that cryptographically secure noise generation with reduced exposure to floating-point vulnerabilities c...
This work formalises this as a framework-agnostic retrieval-to-action provenance graph, classify published attack families by their position relative to it, measure the resulting coverage property against collected agent traces, and falsify the detector's standalone deployment, reversing its own earlier recommendation...
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.
