Do Agents Dream of False Memories? Black-box Visual Attacks on Long-term Memory in Multimodal AI Agents

arXiv:2607.15657 · cs.CR, cs.CV, cs.LG · Submitted 2026-07-17 · Read on arXiv

Halima Bouzidi, Mboutidem Ekemini Mkpong, Mohammad Abdullah Al Faruque

cs.CR, cs.CV, cs.LG

Submitted: 2026-07-17

Comments: 34 pages, 5 figures, 15 tables

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 16× in this paper · explained in 2 episodes
• AI Agents — 13× in this paper · explained in 2 episodes
• Alignment — 11× in this paper · explained in 1 episode
• Embeddings — 11× in this paper · explained in 2 episodes
• Ablation — 9× in this paper · explained in 1 episode
• Cosine Similarity — 9× in this paper · explained in 3 episodes
• Grounding — 9× in this paper · explained in 3 episodes
• Robustness — 9× in this paper · explained in 5 episodes
• Adversarial Attacks — 8× in this paper · explained in 1 episode
• RAG — 8× in this paper · explained in 3 episodes
• LLM judge — 7× in this paper · explained in 2 episodes
• Ablation study — 5× in this paper · explained in 1 episode
• Agent Memory — 5× in this paper · explained in 1 episode
• Consistency — 5× in this paper · explained in 3 episodes
• Absence Recognition — 4× in this paper
• Visual Search — 4× in this paper
• Adversarial Examples — 3× in this paper · explained in 2 episodes
• Adversarial Robustness — 3× in this paper · explained in 3 episodes
• Benchmarking — 3× in this paper · explained in 3 episodes
• Knowledge Revision — 3× in this paper
• Memory Recall — 3× in this paper
• Semantic Drift — 3× in this paper · explained in 3 episodes
• Steering — 3× in this paper · explained in 2 episodes
• Temporal Reasoning — 3× in this paper · explained in 2 episodes
• Time-Tagged Lookup — 3× in this paper
• Visual Reasoning — 3× in this paper
• Adversarial Noise — 2× in this paper · explained in 1 episode
• Failure Modes — 2× in this paper · explained in 3 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• Hallucination — 2× in this paper · explained in 3 episodes
• Transferability — 2× in this paper · explained in 4 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Visual Grounding — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adversarial Transferability — 1× in this paper · explained in 1 episode
• Agentic AI — 1× in this paper · explained in 1 episode
• Decode — 1× in this paper · explained in 2 episodes
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Elias — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Hybrid Approach — 1× in this paper · explained in 4 episodes
• Memory Augmentation — 1× in this paper · explained in 2 episodes
• Provenance — 1× in this paper · explained in 3 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Conversational Health Agents: A Personalized LLM-Powered Agent Framework
• GPT-4 Technical Report
• Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs
• Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents
• Poisoning Attacks against Support Vector Machines
• TeleMem: Building Long-Term and Multimodal Memory for Agentic AI
• Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
• Secure Retrieval-Augmented Generation against Poisoning Attacks
• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• Memory Injection Attacks on LLM Agents via Query-Only Interaction
• AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn
• Retrieval-Augmented Generation for Large Language Models: A Survey
• Explaining and Harnessing Adversarial Examples
• BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
• MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks
• Google's Cloud Vision API Is Not Robust To Noise
• Pre-Storage Reasoning for Episodic Memory: Shifting Inference Burden to Memory for Personalized Dialogue
• MemVerse: Multimodal Memory for Lifelong Learning Agents
• Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs