Related papers: Causality Laundering: Denial-Feedback Leakage in T…

Data contamination poses a significant challenge to reliable LLM evaluation, where models may achieve high performance by memorizing training data rather than demonstrating genuine reasoning capabilities. We introduce RADAR (Recall vs.…

LLM-driven agents are capable of selecting external tools to complete users' tasks. However, attackers could compromise such process, steering agents toward inappropriate/wrong tools and enabling malicious actions. Most existing attacks…

LLM-based agents act through sequences of executable decisions, but their trajectories provide little evidence of which agent or policy produced them, making provenance, ownership, and unauthorized reuse difficult to establish from observed…

Algorithmic auditing has become central to platform accountability under frameworks such as the AI Act and the Digital Services Act. In practice, this obligation is discharged through dedicated Audit APIs. This architecture creates a…

While LLMs exhibit impressive fluency and factual recall, they struggle with robust causal reasoning, often relying on spurious correlations and brittle patterns. Similarly, traditional Reinforcement Learning agents also lack causal…

Large language model (LLM) developers aim for their models to be honest, helpful, and harmless. However, when faced with malicious requests, models are trained to refuse, sacrificing helpfulness. We show that frontier LLMs can develop a…

As AI agents powered by large language models (LLMs) increasingly use external tools for high-stakes decisions, a critical reliability question arises: how do errors propagate across sequential tool calls? We introduce the first theoretical…

Agentic computing systems, while immensely capable, raise serious security, privacy, and safety concerns. A key issue is that the full set of functionalities offered by these systems, combined with their probabilistic execution flows, is…

Even when a tool is explicitly described as unfair and harmful to others, ostensibly safety-aligned LLM agents still voluntarily engage in secret collusion whenever doing so confers a strategic advantage. To investigate this phenomenon, we…

Privacy leakage in LLM agents is often studied through individual storage or execution components, such as memory modules, retrieval pipelines, or tool-mediated artifacts. However, these settings are typically analyzed in isolation, making…

Recent work has shown that gradient updates in federated learning (FL) can unintentionally reveal sensitive information about a client's local data. This risk becomes significantly greater when a malicious server manipulates the global…

Large language model (LLM) agents frequently fail on multi-step tasks involving reasoning, tool use, and environment interaction. While such failures are typically logged or retried heuristically, they contain structured signals about where…

Large Language Model (LLM) agents offer a powerful new paradigm for solving various problems by combining natural language reasoning with the execution of external tools. However, their dynamic and non-transparent behavior introduces…

Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can…

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…

Autonomous agents powered by Large Language Models (LLMs) acquire external functionalities through third-party skills available in open marketplaces. Adopting these integrations broadens the potential attack surface, prompting a need for…

Data rights owners can detect unauthorized data use in large language model (LLM) training by querying with proprietary samples. Often, superior performance (e.g., higher confidence or lower loss) on a sample relative to the untrained data…

Large Language Models (LLMs) are being enhanced with the ability to use tools and to process multiple modalities. These new capabilities bring new benefits and also new security risks. In this work, we show that an attacker can use visual…

Machine learning components are now central to AI-infused software systems, from recommendations and code assistants to clinical decision support. As regulations and governance frameworks increasingly require deleting sensitive data from…

Previous benchmarks on prompt injection in large language models (LLMs) have primarily focused on generic tasks and attacks, offering limited insights into more complex threats like data exfiltration. This paper examines how prompt…