Related papers: No Attacker Needed: Unintentional Cross-User Conta…
Warning: this paper contains content that maybe offensive or upsetting. Recent research in Natural Language Processing (NLP) has advanced the development of various toxicity detection models with the intention of identifying and mitigating…
Traditional, centralized security tools often miss adaptive, multi-vector attacks. We present the Multi-Agent LLM Cyber Defense Framework (MALCDF), a practical setup where four large language model (LLM) agents-Detection, Intelligence,…
Unsupervised Text Style Transfer (UTST) has emerged as a critical task within the domain of Natural Language Processing (NLP), aiming to transfer one stylistic aspect of a sentence into another style without changing its semantics, syntax,…
When an LLM agent fails a multi-step tool-augmented task and retries, the failed attempt typically remains in its context window -- contaminating the next attempt and elevating the per-step error rate beyond the base level. This…
Post-mortem analysis of compromised systems is a key aspect of cyber forensics, today a mostly manual, slow, and error-prone task. Agentic AI, i.e., LLM-powered agents, is a promising avenue for automation. However, applying such agents to…
Execution-aware LLM agents offer a promising paradigm for learning from tool feedback, but such feedback is often expensive and slow to obtain, making online reinforcement learning (RL) impractical. High-coverage hardware verification…
Computer-use agents (CUAs) can now autonomously complete complex tasks in real digital environments, but when misled, they can also be used to automate harmful actions programmatically. Existing safety evaluations largely target explicit…
Large language models (LLMs) are increasingly deployed in human-AI teams as support agents for complex tasks such as information retrieval, programming, and decision-making assistance. While these agents' autonomy and contextual knowledge…
A high volume of recent ML security literature focuses on attacks against aligned large language models (LLMs). These attacks may extract private information or coerce the model into producing harmful outputs. In real-world deployments,…
Since the official release of ChatGPT in 2022, large language models (LLMs) have rapidly evolved from chatbot-style interfaces into agentic systems that can delegate work through tools and newly spawned subagents. While these capabilities…
Documenting tacit knowledge in organizations can be a challenging task due to incomplete initial information, difficulty in identifying knowledgeable individuals, the interplay of formal hierarchies and informal networks, and the need to…
LLM-powered agents are beginning to automate user's tasks across the open web, often with access to user resources such as emails and calendars. Unlike standard LLMs answering questions in a controlled ChatBot setting, web agents act "in…
LLM agents increasingly draft messages on behalf of users, yet users routinely overshare sensitive information and disagree on what counts as private. Existing systems support only suppression (omitting sensitive information) and…
In this work, we consider the consensus problem in which legitimate agents share their values over an undirected communication network in the presence of malicious or faulty agents. Different from the previous works, we characterize the…
As multi-agent architectures and agent-to-agent protocols proliferate, a fundamental question arises: what actually happens when autonomous LLM agents interact at scale? We study this question empirically using data from Moltbook, an…
Graphical user interface (GUI) agents built on multimodal large language models (MLLMs) have recently demonstrated strong decision-making abilities in screen-based interaction tasks. However, they remain highly vulnerable to pop-up-based…
As Large Language Models (LLMs) are increasingly integrated into automated, multi-stage pipelines, risk patterns that arise from unvalidated trust between processing stages become a practical concern. This paper presents a…
The growing deployment of large language model (LLM) based agents that interact with external environments has created new attack surfaces for adversarial manipulation. One major threat is indirect prompt injection, where attackers embed…
Computer-use agent (CUA) frameworks, powered by large language models (LLMs) or multimodal LLMs (MLLMs), are rapidly maturing as assistants that can perceive context, reason, and act directly within software environments. Among their most…
Collaborative spectrum sensing can significantly improve the detection performance of secondary unlicensed users (SUs). However, the performance of collaborative sensing is vulnerable to sensing data falsification attacks, where malicious…