REVIEW 17 cited by
Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
read the original abstract
A multimodal large language model (MLLM) agent can receive instructions, capture images, retrieve histories from memory, and decide which tools to use. Nonetheless, red-teaming efforts have revealed that adversarial images/prompts can jailbreak an MLLM and cause unaligned behaviors. In this work, we report an even more severe safety issue in multi-agent environments, referred to as infectious jailbreak. It entails the adversary simply jailbreaking a single agent, and without any further intervention from the adversary, (almost) all agents will become infected exponentially fast and exhibit harmful behaviors. To validate the feasibility of infectious jailbreak, we simulate multi-agent environments containing up to one million LLaVA-1.5 agents, and employ randomized pair-wise chat as a proof-of-concept instantiation for multi-agent interaction. Our results show that feeding an (infectious) adversarial image into the memory of any randomly chosen agent is sufficient to achieve infectious jailbreak. Finally, we derive a simple principle for determining whether a defense mechanism can provably restrain the spread of infectious jailbreak, but how to design a practical defense that meets this principle remains an open question to investigate. Our project page is available at https://sail-sg.github.io/Agent-Smith/.
Forward citations
Cited by 17 Pith papers
-
Confused ChatGPT: Cross-App Context Poisoning via First-Party APIs
Identifies cross-app context poisoning in ChatGPT Apps, a persistent indirect prompt injection delivered through undocumented first-party API parameters that lets one app manipulate others via the shared untagged context.
-
Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems
Prompt injection attacks can self-replicate across LLM agents in multi-agent systems, enabling data theft, misinformation, and system disruption while propagating silently.
-
MEMSAD: Gradient-Coupled Anomaly Detection for Memory Poisoning in Retrieval-Augmented Agents
MEMSAD links anomaly detection gradients to retrieval objectives under encoder regularity to certify detection of continuous memory poisons, achieving perfect TPR/FPR in experiments while exposing a synonym-invariance gap.
-
MEMSAD: Gradient-Coupled Anomaly Detection for Memory Poisoning in Retrieval-Augmented Agents
MEMSAD uses a provable gradient coupling between anomaly detection and retrieval objectives to deliver certified detection of memory poisoning in LLM agents, achieving optimal sample complexity and perfect TPR/FPR in ...
-
A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework
A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
-
Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization
The work creates a new benchmark for humanizing GUI agent touch dynamics via a MinMax detector-agent model, a mobile touch dataset, and methods showing agents can match human behavior without losing task performance.
-
Unifying Adversarially Robust Model Experts in Vision-Language Models
CARE collaboratively fine-tunes two CLIP experts (image-text alignment and image-invariance) with embedding harmonization and EMA merging, yielding a single model with better clean and adversarial accuracy than either expert.
-
Even More Deception: Objective Misalignment in Mixed-Motive LLM Multi-Agent Systems
Changing one LLM agent's secret objective in Werewolf lowers its team's win rate and changes its reasoning, while its public chat stays deceptively normal.
-
MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems
MESA ranks MAS communication edges by vulnerability via graph-theoretic metrics and dynamic probes, achieving mean Spearman ρ=+0.60 correlation with empirical per-edge attack success and 3x interception gain when moni...
-
POISE: Position-Aware Undetectable Skill Injection on LLM Agents
POISE is a stealthy skill-poisoning attack achieving 89.3% ASR on Skill-Inject by blending a compressed trigger into contextually appropriate positions in skill bodies, outperforming YAML and random-placement baseline...
-
Defending LLM-based Multi-Agent Systems Against Cooperative Attacks with Sentence-Level Rectification
STAR defense mitigates cooperative attacks in LLM-based multi-agent systems, improving task success rate by 36.76% on average while cooperative attacks cause a 5.34% relative drop compared to independent attacks.
-
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs
MemJack achieves 71.48% attack success rate on unmodified COCO val2017 images against Qwen3-VL-Plus by coordinating agents to map visual entities to malicious intents, apply multi-angle camouflage, and filter refusals...
-
Agents at Risk: How Users Unwittingly Undermine LLM Safety
Commercial AI agents routinely trust user-relayed unverified content and execute risky actions unless the user explicitly demands a safety check.
-
A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?
A survey that defines Computer-Using Agents for safety analysis, categorizes their threats, proposes a taxonomy of defensive strategies, and summarizes benchmarks and datasets for evaluating CUA safety and performance.
-
Conversations Risk Detection LLMs in Financial Agents via Multi-Stage Generative Rollout
FinSec is a multi-stage detection system for financial LLM dialogues that reaches 90.13% F1 score, cuts attack success rate to 9.09%, and raises AUPRC to 0.9189.
-
Large Language Model Agent: A Survey on Methodology, Applications and Challenges
A survey that deconstructs LLM agent systems via a methodology-centered taxonomy linking design principles to emergent behaviors, applications, and challenges.
-
LLM-Powered AI Agent Systems and Their Applications in Industry
A survey categorizing LLM-powered agent systems into software-based, physical, and hybrid types, covering industrial applications and challenges such as latency and security.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.