Related papers: Trojan Hippo: Weaponizing Agent Memory for Data Ex…

AI-agent guardrails are memoryless: each message is judged in isolation, so an adversary who spreads a single attack across dozens of sessions slips past every session-bound detector because only the aggregate carries the payload. We make…

Recent advances in Trajectory Optimization (TO) models have achieved remarkable success in offline reinforcement learning. However, their vulnerabilities against backdoor attacks are poorly understood. We find that existing backdoor attacks…

Advanced Persistent Threats (APTs) represent a growing menace to modern digital infrastructure. Unlike traditional cyberattacks, APTs are stealthy, adaptive, and long-lasting, often bypassing signature-based detection systems. This paper…

Backdoor attacks embed malicious behaviors into Large Language Models (LLMs), enabling adversaries to trigger harmful outputs or bypass safety controls. However, the persistence of the implanted backdoors under user-driven post-deployment…

Large Language Model (LLM)-based agents with function-calling capabilities are increasingly deployed, but remain vulnerable to Indirect Prompt Injection (IPI) attacks that hijack their tool calls. In response, numerous IPI-centric defense…

Large language models (LLMs) have raised concerns about potential security threats despite performing significantly in Natural Language Processing (NLP). Backdoor attacks initially verified that LLM is doing substantial harm at all stages,…

Existing AI agent safety benchmarks focus on generic criminal harm (cybercrime, harassment, weapon synthesis), leaving a systematic blind spot for a distinct and commercially consequential threat category: agents harming their own…

Large language models (LLMs) are increasingly augmented with long-term memory systems to overcome finite context windows and enable persistent reasoning across interactions. However, recent research finds that LLMs become more vulnerable…

Agentic memory enables LLMs to persist information beyond a single context window and reuse it in later decisions, but it also introduces a new vulnerability: spurious correlations, where retrieved memory carries miscorrelated evidence and…

The evolution from static ranking models to Agentic Recommender Systems (Agentic RecSys) empowers AI agents to maintain long-term user profiles and autonomously plan service tasks. While this paradigm shift enhances personalization, it…

As large language models (LLMs) become integrated into sensitive workflows, concerns grow over their potential to leak confidential information. We propose TrojanStego, a novel threat model in which an adversary fine-tunes an LLM to embed…

As LLM-based agents are increasingly used in long-term interactions, cumulative memory is critical for enabling personalization and maintaining stylistic consistency. However, most existing systems adopt an ``all-or-nothing'' approach to…

The increasing integration of Large Language Model (LLM) based search engines has transformed the landscape of information retrieval. However, these systems are vulnerable to adversarial attacks, especially ranking manipulation attacks,…

Securing AI agents powered by Large Language Models (LLMs) represents one of the most critical challenges in AI security today. Unlike traditional software, AI agents leverage LLMs as their "brain" to autonomously perform actions via…

As large language model (LLM)-powered agents are increasingly deployed to perform complex, real-world tasks, they face a growing class of attacks that exploit extended user-agent-environment interactions to pursue malicious objectives…

Large language model (LLM) agents achieve impressive single-task performance but commonly exhibit repeated failures, inefficient exploration, and limited cross-task adaptability. Existing reflective strategies (e.g., Reflexion, ReAct)…

Advanced persistent threats (APT) combine a variety of different attack forms ranging from social engineering to technical exploits. The diversity and usual stealthiness of APT turns them into a central problem of contemporary practical…

Large Language Model (LLM)-based agents exhibit significant potential across various domains, operating as interactive systems that process environmental observations to generate executable actions for target tasks. The effectiveness of…

Memory-augmented LLM agents tackle complex long-horizon tasks by recursively summarizing interaction trajectories into compact memory. However, existing approaches typically train these memory policies using outcome-based reinforcement…

Machine learning is becoming increasingly popular as a go-to approach for many tasks due to its world-class results. As a result, antivirus developers are incorporating machine learning models into their products. While these models improve…