arXiv Machine Learning
Jun 4
Bypassing Prompt Guards in Production with Controlled-Release Prompting
arXiv:2510. 01529v3 Announce Type: replace Abstract: Ball et al.
MAS-Shield: A Defense Framework for Secure and Efficient LLM MAS
MAS-Shield is a defense framework for Large Language Model–based Multi-Agent Systems that uses a coarse‑to‑fine filtering pipeline. It first selects critical agents, then applies lightweight auditing to most cases, and finally escalates only suspicious signals to a heavyweight committee. Experiments show a 92.5% recovery rate against adversarial attacks and a latency reduction of over 70% compared to existing methods.
Related stories
arXiv AI
Jun 30
MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems
arXiv:2606. 30602v1 Announce Type: cross Abstract: Multi-agent systems (MAS) are increasingly used to automate complex, distributed workflows.
arXiv Machine Learning
Jul 1
When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systems
arXiv:2605. 01133v3 Announce Type: replace-cross Abstract: Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks.
arXiv AI
Sep 16
Universal Defenses for Tool-Integrated LLM Agents Against Adversarial Attacks
The paper proposes universal, tool‑based defenses for large language model agents that use external tools, addressing four types of adversarial attacks: direct and indirect prompt injection, memory poisoning, and backdoor attacks. Two main defenses are introduced: Attacker Tool Filtering, which uses anomaly detection to remove suspicious tools, and Normal Tool Recalling, which restores the agent’s original toolset before planning. The authors also add prompt‑based defenses such as Chain‑of‑Thought prompting and self‑reflection, and demonstrate that these methods dramatically lower attack success rates—often to 0%—across multiple open‑source and proprietary LLMs while maintaining or improving task performance.
arXiv AI
Sep 15
ActGuard: Pre-execution Action Auditing against Indirect Prompt Injection in LLM Agents
arXiv:2609.14987v1 Announce Type: cross Abstract: Large language model (LLM) agents interact with external environments through tool invocation, but tool outputs can also expose them to indirect prom...
arXiv Computation and Language
Sep 21
CASCADE Against Jailbreaks: Combination Across Stages with Controlled Attack-Defense Evaluation
The paper presents a systematic study of combining defenses against jailbreak attacks on Large Language Models across different pipeline stages. It introduces a standardized evaluation framework that defines attack-success-rate, controls query budgets, and applies explicit fairness rules. Across 19 attacks and 15 defenses, the study finds that no single defense dominates, but carefully selected combinations can provide strong safety with minimal loss of utility, offering practical guidance for layered defense pipelines.
arXiv AI
Sep 2
SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems
arXiv:2609.00595v1 Announce Type: cross Abstract: Safe agents can fail together. Multi-agent LLM systems (MAS) move information, state, decisions, and authority across principal boundaries, creating...
arXiv AI
Jul 24
GuardianAgentBench: Where Agents Fail and How to Guard Them
arXiv:2607. 20982v1 Announce Type: new Abstract: As large language model agents increasingly operate autonomously with access to tools and external environments, ensuring their safe and reliable behavior becomes critical.
arXiv AI
Jul 14
A Low-Latency Fraud Detection Layer for Detecting Adversarial Interaction Patterns in LLM-Powered Agents
arXiv:2605. 01143v2 Announce Type: replace Abstract: Large Language Model (LLM)-powered agents demonstrate strong capabilities in autonomous task execution, tool use, and multi-step reasoning.
arXiv AI
Jun 10
Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation
arXiv:2606. 10749v1 Announce Type: cross Abstract: Large language model (LLM) agents are rapidly moving from conversational interfaces to software components that plan, invoke tools, maintain memory, and act on external environments.
arXiv AI
Jun 12
PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt Injections
arXiv:2606. 12737v1 Announce Type: cross Abstract: Large Language Models (LLMs) are rapidly evolving into agentic systems that interact with external tools and environments, introducing new security risks such as indirect prompt injection attacks through untrusted external sources.
arXiv AI
Jul 23
ChannelGuard: Safe Models Do Not Compose into Safe Multi-Agent Systems
arXiv:2607. 19430v1 Announce Type: cross Abstract: Multi-agent LLM applications chain a planner, worker agents, a verifier, and a synthesizer, and every hop between agents is an unmonitored channel through which an adversary can smuggle instructions.