After the Attacker Leaves: Benchmarking Carryover Attacks on LLM Agents
Modern LLM agents persist state across sessions via two channels: long-lived memory files silently prepended to the syst
#cs.AI
共收录 1652 条相关情报。
← 返回所有主题MAS-Guard: Unified Guardrails from Individual Agents to Multi-Agent LLM Systems
Agentic AI extends large language models (LLMs) from generating responses to planning and executing complex workflows, s
Context-Aware Prompt Injection Detection via Small Language Models in RAG Pipelines: nokast-secureRAG
Local Retrieval-Augmented Generation (RAG) systems are vulnerable to indirect prompt injection and retrieval poisoning,
ClawMMU: Protection-Coherent Virtual Memory for Stateful LLM Agents
AI agents keep long-term memory, much of which comes from web pages and tool results. Agent harnesses, the software that
Self-Evolving Static Analysis via LLM Pseudo-Labeling
Security bugs often slip past static analysis not because they are impossible to detect, but because detection rules hav
A Unified Attack Framework against Statistical Generative Watermarks for Large Language Models
Watermarking has emerged as a key tool for identifying text generated by large language models (LLMs), with current sche
Local Allow, Global Deny: Why Per-Action Authorization Does Not Compose in LLM Agents
Autonomous LLM agents act through tools under per-action authorization: a local guard screens each tool call in isolatio
The Show-Up Attack: When Subagents Win Over Their Supervisor
Multi-agent systems are increasingly deployed to coordinate multiple large language model (LLM) agents. However, this al
Act on Your Behalf, Beyond Your Authorization: Benchmarking LLM Agent Authorization Alignment
When an LLM agent acts on behalf of a user, it is expected to act within the authorization scope the user grants. Existi
Adversarial Benchmarks and BenchDoor Attacks: Exploiting Benchmark Incentives for Backdoor Attacks
Machine learning benchmarks act as guideposts for model development and spur the creation of training datasets intended
Beyond the Prompt: Recovering Hidden Concepts in Text-to-Image Models
Text-to-image models can generate visual concepts that their prompts never mention, and recent work shows that such asso
Privacy-Preserving Personalized Federated Learning (PPP-FL) for Medical Imaging
Federated learning (FL) is a distributed machine learning paradigm that reduces transmission costs, mitigates cross-bord
Exposing Vulnerability Monoculture Through Systemic Adversarial Robustness
Beneath the apparent diversity of foundation models lies an increasingly homogeneous technical stack of common training
Global Security Blind Spots: Translation as a Safety Bypass in Low-Resource Languages
Large language models are deployed globally, yet safety alignment and evaluation remain concentrated in English: harmful
When Models Know but Can't Linearly Say: Relational Encoding Limits Linear Vulnerability Classification in Code LLMs
Large language models can detect vulnerable code, yet the form of vulnerability encoding in their representations remain
AutoRedClaw: Automated Red-Teaming for Claw-Style Agents
Agent systems are shifting from task-scoped tool-use agents to persistent, personalized assistants such as OpenClaw. The
Profile-DP: Differential Privacy for User-Controlled Profile Release in Personalized LLM Inference
Personalized large language models (LLMs) increasingly rely on profile-conditioned inference, pairing public requests wi
Model Exposure on One Device Endangers Others: Rethinking Edge Neural Network Security across Devices
Neural networks (NNs) are increasingly deployed on edge devices such as mobile and IoT platforms, offering low latency a
Mind Your Boundaries: Boundary-Aware Model Obfuscation against Cross-node Attack
With the advancement of powerful AI chips, on-device machine learning is gaining traction for its low latency and privac
Game of Phones: Harnessing Game Theory and LLMs in 'Bot Wars' to Counteract Phone Scams
Phone scams impose substantial and growing costs on individuals and financial systems worldwide, yet existing countermea