Poster: A Preliminary Study of LLM Distillation Inference
Unauthorized model distillation, in which a model is trained on the outputs of a proprietary large language model (LLM),
2026-10-09 归档
今日共收录 747 条安全情报，包含 0 个 CVE，359 篇安全通告，以及 100 篇研究论文。
← 返回归档列表Could LLM Watermark Detection be Public?
Watermarking large language models is popular for tracing chatbot and agentic outputs, yet detectors remain unreleased s
SemField: A Simple, Linear, Continuous, yet Robust Semantic Watermark
The rapid proliferation of Large Language Models (LLMs) necessitates reliable watermarking techniques to identify AI-gen
Anytime-valid detection of LLM weight exfiltration
A compromised LLM inference server can leak model weights by encoding payload bits in otherwise plausible token choices.
Where Do the Tokens Go? Understanding and Reducing Costs in LLM Agents for Vulnerability Discovery
LLM agents can spend millions of tokens during vulnerability discovery without producing a working proof of concept (PoC
Skill Constellations: Tracing the Supply Chain of Agent Skills on GitHub
Agent skills are SKILL.md instructions and scripts that AI coding agents such as Claude Code and Codex run with the perm
Characterizing Statistical Separability in TP-CRIV for Probabilistic AI Models
Third-party challenge-response identity verification (TP-CRIV) enables an independent verifier to assess whether a claim
NOMOS: Compiling Written Policies into Statically Verified Tool-Call Gates for LLM Agents
Tool-using LLM agents violate the policies they are deployed to enforce, often silently. Prior defenses hand-write rules
Speedbumps: Rejection Attacks on Speculative Decoding
Speculative decoding is a popular technique for increasing the speed and reducing the costs of large language model (LLM
BRANCH: Bypassing Multi-Scanner AI Guardrails
AI systems increasingly rely on Large Language Models (LLMs) as core reasoning engines, making them targets for prompt i
DITTO: A Context-aware Pickle-based Pre-Trained Model Scanner for Effective Security Audits
Pre-trained models (PTMs) are widely distributed as serialized binaries, but their reuse often exposes software supply c
SLDR: Defending Against Malicious Fine-tuning via Selective Layers Recovery and Dynamic Routing
Fine-tuning-as-a-service enables users to adapt aligned large language models (LLMs) to specialized tasks, but malicious
PatchBench: Measuring Collateral Damage in Activation Patching
An LLM safety patch can pass a benchmark while still being a poor repair. This risk is especially acute for jailbreak re
On the Reliability of LLM-Based Vulnerability Patching Benchmarks
Large language models (LLMs) have shown strong potential for automated vulnerability patching, but current benchmarks ca
Constrained-Action AI Remediation for SIEM/XDR via a NeMo-Guardrails Proxy
Security Operations Centers (SOCs) for information technology and operational technology share one incident-response pro
Formal Runtime Verification for Tool-Using LLM Agents: An Offline Same-Benchmark Study on AgentDojo and STAC
Guardrails for tool-using LLM agents are usually application-specific rules, which makes multi-step, data-dependent safe
Correct Answers, Unsupported Findings: Evidence Binding in Forensic Reconstruction of LLM Agent Logs
Forensic reconstruction of LLM-agent actions requires not only recovering the correct value, but establishing which pres
MARS: Malware Analysis with Rule-Based Scoring of LLM Claims
Large language models can triage malware through direct verdicts or behavioral claims scored by an external policy. We p
Ask the Expert: LLM-Guided Reinforcement Learning for Autonomous Cyber Defense
Policy-based reinforcement learning (RL) approaches have produced promising results for autonomous cyber defense; howeve
Package Hallucination Attacks on Coding Agents through Prompt Injection in Rule Files
Modern agentic coding frameworks increasingly rely on community-shared rule files (e.g., AGENTS.md or .cursorrules) to g