Category
1,407 papers
Diffusion models have emerged as the foundation of modern generative systems, yet their high memorization capacity raises privacy concerns. While differentially private (DP) training provides formal guarantees, it comes at a cost in sample quality. In this work, we study a complementary question: how much privacy loss...
Pipelines that combine large language models (LLMs) with static analysis let the model consume the analyser's output as evidence, but whether the model distinguishes true from false evidence, and whether its scrutiny depends on what the evidence claims, has not been measured. We built an intraprocedural analyser for C/...
Vision-Language Models (VLMs) are widely deployed, yet the internal mechanisms behind their safety behavior remain poorly understood. We present a lightweight inference-time framework for localizing and manipulating safety-sensitive representations in frozen VLMs, without retraining or modifying parameters. On Qwen3-VL...
As large language models (LLMs) face growing demands for data removal driven by regulatory compliance, copyright concerns, and privacy protection, approximate unlearning has emerged as a practical alternative to expensive full retraining. In practice, pre- and post-unlearning model snapshots are often maintained for au...
Reach audiences
Advertise in front of researchers, engineers, and readers.
WebAssembly (Wasm) enables near-native performance for web applications through a portable and sandboxed execution model. However, its limited runtime protection mechanisms (e.g., the lack of stack canaries and address space layout randomization (ASLR)) leave Wasm applications vulnerable to traditional attacks. We pres...
Safety guards check content before an LLM application acts on it, and most paste that content into a plain-text prompt. Content that imitates the prompt can append a second task, and the guard answers that one instead. We call this target rebinding. Our explanation is that the guard grades the last complete task in its...
Differentially Private Stochastic Gradient Descent (DPSGD) has become the de facto standard for training deep neural networks with rigorous privacy guarantees. However, the utility of DPSGD is constrained by gradient clipping bias and DP noise. While existing work has tried to address these issues, the geometric misali...
AI-text detectors are increasingly used in high-stakes settings, but their robustness to meaning-preserving adversarial rewriting remains unclear. We introduce StealthRL, a reinforcement learning framework for stress-testing detectors with adaptive paraphrase attacks. StealthRL trains a paraphrase policy against a dete...
Agent safety is moving from content moderation toward preventing operational failures before tool-using agents act. We propose Janus, a foresight-oriented framework for long-horizon agent safety that trains guards to anticipate delayed risks from partial trajectories. Janus synthesizes diverse agent trajectories via mu...
AI agents can inspect code and run tests to support smart contract security. SlowMist reports about $38.6 billion in losses across the broader blockchain ecosystem. Existing evaluations can reward memorized or copied answers, including attack code recovered from public blockchain transactions. Reconstructing contracts...
Pre-trained code models are exposed to backdoor poisoning, in which crafted training samples make the model misbehave on a trigger. A capable attacker minimizes the number of such samples, since each adds cost and exposure and a lower poisoning rate leaves a smaller footprint for defenses. Which samples to poison there...
Verifying the provenance of autonomous LLM agents is a critical security challenge. Existing semantic attribution is easily obfuscated by system prompts, while active watermarking conflicts with schema-constrained tool generation. We propose AgentTrace, an active framework that identifies the foundation model behind a...
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.
