Token-Level Attribution of Multi-Mode LLM Watermarks: Optimal Rule and Belief Weighting
A watermark verifier may hold many modes, i.e., secret keys, and a document may mix spans of different modes with unwate
2026-10-19 归档
今日共收录 660 条安全情报，包含 0 个 CVE，346 篇安全通告，以及 66 篇研究论文。
← 返回归档列表Monitor-Validity Failures: LLM Safety Evidence Paths at Evolving Framework Boundaries
Modern LLM applications rely on runtime monitors that inspect tool calls, traces, streams, detector outputs, and verifie
MobileInject: Evaluating Reasoning-to-Action Security of MLLM-Based Mobile Agents under Cross-Modal Consistency Injection
Multimodal large language model (MLLM)-based mobile agents are rapidly evolving from conversational assistants into auto
MobileJailBench: Red Queen Jailbreak Benchmarking for Mobile Agents
MLLM-based mobile agents are rapidly gaining autonomy in perception, planning, and closed-loop execution in dynamic mobi
Ignored, Not Refused: What Low Prompt-Injection Success Rates Hide in Small Tool-Using Agents
Tool-using agents read untrusted external content, which exposes them to indirect prompt injection (IPI), where hidden i
AgentLoupe: Kernel-Resident Semantic Causal Labels for AI Agent Observability
AI agents translate user intents into system actions via tool invocations. Accurately attributing these actions to their
From GAN-Based Models to GPT-5: A Taxonomy-Guided Study of Human Performance in Detecting Deepfake Face Images
Generative models for deepfakes have rapidly evolved from GAN-based architectures to diffusion models and multimodal lar
VulnSAGE: Adjudicating SAST Reports by Connecting LLM Reasoning to Program Structure
Static Application Security Testing (SAST) reports flag operations whose safety depends on project-specific context, and
SAFE-Mem: Secure Agentic Memory with Fine-Grained Authority and Governance-Aware Retrieval
Large language model (LLM) agents increasingly rely on persistent memory to support long-term reasoning and personalized
When Core-Network Elements Become Reachable: Field-Level Exploitability Analysis in Diameter
The increasing exposure of cellular core-network elements to public networks has turned Diameter signaling interfaces in
Identify, Classify, Act: Per-Instruction Controlled Compliance for LLMs over External Data
LLMs over external data face a per-instruction tension: a single document or tool return often interleaves legitimate di
Stealthy Poisoning Attacks via Reused KV Cache of Reasoning
Modern large language model (LLM) systems reuse key-value (KV) caches to accelerate inference. Recent work has shown tha
GRAD: Graph-Structured Antibody Defense for LLM Agents
Memory poisoning and decomposition attacks distribute malicious evidence across the operations of large language model a
Veil-Then-Reveal: Protecting PII Privacy via Reversible Pseudo-Anonymization in Zero-Trust User--LLM Interaction
Large language models (LLMs) increasingly process sensitive documents and personal information, yet sending prompts cont
The LLM-Attacker: A Unified Red-Team Framework for Privacy Evaluation of Split and Distributed LLM Systems
Split language models keep input text on a client but send intermediate representations to a server. Attacks can reconst
ACE: An AI-Orchestrated Intrusion Detection and Compliance Mapping Engine
This study proposes the Automated Compliance Engine (ACE), an AI-orchestrated framework that links intrusion detection,
What It Is, Not What It Says: Securing Agentic Browsing Interactions with Web Semantics
AI agents increasingly browse the web on users' behalf, yet they consume webpages as screenshots or text, exposing their
Can SOLARBURST go silicon? A systematic analysis on software supply chain attacks for VLSI design flows
An attacker targeting the software supply chain (SWSC) of VLSI tools can fully subvert the VLSI design pipeline through
BiShield-TEE: On the (In-)Security of Unilateral Weight Obfuscation in On-Device TEE-Shielded LLM Partition
On-device deployment of large language models (LLMs) is increasingly adopted due to latency and privacy requirements, bu
What Survives Self-Evolution: Provenance Marks in Copied Agent Harnesses
Agent harnesses, the prompt and tool code around a base model, leak. Claude Code's 512,000 lines were mirrored within ho