Related papers: TraceAegis: Securing LLM-Based Agents via Hierarch…
As LLM-based agents increasingly browse the web on users' behalf, a natural question arises: can websites passively identify which underlying model powers an agent? Doing so would represent a significant security risk, enabling targeted…
Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents through tool use, planning, and decision-making abilities, leading to their widespread adoption across diverse tasks. As task complexity grows,…
The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…
With the rapid advancement and adoption of Audio Large Language Models (ALLMs), voice agents are now being deployed in high-stakes domains such as banking, customer service, and IT support. However, their vulnerabilities to adversarial…
Modern agentic frameworks (e.g., CrewAI and AutoGen) have evolved into complex, autonomous multi-agent systems, introducing unique reliability challenges beyond earlier pipeline-based LLM libraries. However, existing empirical studies focus…
Ensuring the safe use of agentic systems requires a thorough understanding of the range of malicious behaviors these systems may exhibit when under attack. In this paper, we evaluate the robustness of LLM-based agentic systems against…
AI-based systems, including Large Language Models (LLM), impact millions by supporting diverse tasks but face issues like misinformation, bias, and misuse. AI ethics is crucial as new technologies and concerns emerge, but objective,…
The robustness of LLMs to jailbreak attacks, where users design prompts to circumvent safety measures and misuse model capabilities, has been studied primarily for LLMs acting as simple chatbots. Meanwhile, LLM agents -- which use external…
AI agents are increasingly embedded in real software systems, where they execute multi-step workflows through multi-turn dialogue, tool invocations, and intermediate decisions. These long execution histories, called agentic traces, make…
Web agents enable users to perform tasks on web browsers through natural language interaction. Evaluating web agents trajectories is an important problem, since it helps us determine whether the agent successfully completed the tasks.…
Agents built on LLMs are increasingly deployed across diverse domains, automating complex decision-making and task execution. However, their autonomy introduces safety risks, including security vulnerabilities, legal violations, and…
The rise of large language model (LLM)-based multi-agent systems (MAS) introduces new security and reliability challenges. While these systems show great promise in decomposing and coordinating complex tasks, they also face multi-faceted…
Large language model (LLM)-based agents increasingly rely on tool use to complete real-world tasks. While existing works evaluate the LLMs' tool use capability, they largely focus on the final answers yet overlook the detailed tool usage…
The integration of Large Language Models (LLMs) into wearable sensing is creating a new class of mobile applications capable of nuanced human activity understanding. However, the reliability of these systems is critically undermined by…
LLM-driven GUI agents are increasingly used in production systems to automate workflows and simulate users for evaluation and optimization. Yet most GUI-agent evaluations emphasize task success and provide limited evidence on whether agents…
As Large Language Models (LLMs) and generative AI become increasingly widespread, concerns about content safety have grown in parallel. Currently, there is a clear lack of high-quality, human-annotated datasets that address the full…
We introduce AegisLLM, a cooperative multi-agent defense against adversarial attacks and information leakage. In AegisLLM, a structured workflow of autonomous agents - orchestrator, deflector, responder, and evaluator - collaborate to…
Anomaly detection in event logs is a promising approach for intrusion detection in enterprise networks. By building a statistical model of usual activity, it aims to detect multiple kinds of malicious behavior, including stealthy tactics,…
As large language models (LLMs) are increasingly deployed as agents, their integration into interactive environments and tool use introduce new safety challenges beyond those associated with the models themselves. However, the absence of…
Autonomous LLM agents generate multi-step action plans that can fail due to contextual misalignment or structural incoherence. Existing anomaly detection methods are ill-suited for this challenge: mean-pooling embeddings dilutes anomalous…