Category
1,407 papers
This work introduces and formalizes context-inference attacks through a security game and evaluates three settings under decreasing attacker knowledge and increasingly indirect delivery of the context: a known context, an unknown context, and a context the agent retrieves through its own tool calls.
LLMs are trained to generate natural language. However, various strands of evidence indicate that an LLM's externalized linguistic outputs and mechanistically-extracted linguistic features can be an unreliable lens for understanding internal model computation. We introduce the term ``linguistic illegibility'' to broadl...
The first systematic study of poisoning-based backdoor attacks on Speech Emotion Recognition systems with a focus on threats enabled by text-to-speech (TTS) generated audio is presented, revealing that TTS technology dramatically lowers the barrier to effective backdoor attacks.
Results show that TOP-R requires defenses beyond prompting alone, and introduces Library-Grounded Reverse-Inference Seed Expansion (LRSE), a four-library reverse-construction pipeline, and proposes TOP-Align, an SFT+DPO method for learning safer task-completion boundaries.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Results show that LLM-based vulnerability injection is feasible, while exposing key limitations in scalability and diversity, and practical challenges including LLMs' non-determinism and the difficulty of preserving contract semantics are reported.
Mixture-of-Experts (MoE) is a scaling architecture for large language models that activates only a small subset of expert modules per token, enabling massive parameter growth with nearly constant computation. Recent Hybrid MoE architecture adds \textit{shared experts} to capture consistently useful representations, fur...
A self-referential retrosynthesis framework for explainable AI provenance forensics under a fixed-generator setting that leverages a jointly optimized encoder-decoder pair to implement a self-embedding mechanism that enables round-trip consistency verification.
Motivated by the observation that safety signals from unsafe text processing can be transferred, safety-awareness representation transfer (SRT) is proposed, a lightweight direction-refinement method that mitigates cross-modal safety drift with a frozen MLLM backbone.
This work evaluates five LLMs as memory writers and two as executors across procurement, cybersecurity, and finance and introduces EAL-Bench, which measures how accurately persistent memory preserves evolving authorization state and whether errors propagate to downstream unauthorized actions.
This work introduces Homomorphic Encryption-Aware Training (HEAT), a fine-tuning method that makes the per-nonlinearity iteration counts learnable, enabling them and the model weights to co-adapt during training.
This work measures one such behavior in a single controlled MCP-to-A2A configuration: a testbed drives a real-model host across a local MCP and a local A2A leg into an ordered event trace scored by exact deterministic rules (no LLM judge).
To separate component effects from matcher rewards, CTIForge is built, whose deterministic validation layer can vary while extraction is held byte-identical, and which coincides with a roughly 2.8-fold increase in actions explicitly disputing entity type.
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.
