Related papers: Structured Security Auditing and Robustness Enhanc…
Reproducibility problems that have long affected machine learning and reinforcement learning are now surfacing in agent research: papers compare systems by reported scores while leaving the rollout records behind those scores difficult to…
With the rapid progress of large language models (LLMs), LLM-powered multi-agent systems (MAS) are drawing increasing interest across academia and industry. However, many current MAS frameworks struggle with reliability and scalability,…
Autonomous agent frameworks built upon large language models (LLMs) are evolving into complex, tool-integrated, and continuously operating systems, introducing security risks beyond traditional prompt-level vulnerabilities. As this paradigm…
AI agents that interact with their environments through tools enable powerful applications, but in high-stakes business settings, unintended actions can cause unacceptable harm, such as privacy breaches and financial loss. Existing…
Hard-gated safety checkers often over-refuse and misalign with a vendor's model spec; prevailing taxonomies also neglect robustness and honesty, yielding safer-on-paper yet less useful systems. This work introduces Guardian-as-an-Advisor…
Large Language Model (LLM) providers expose fine-tuning APIs that let end users fine-tune their frontier LLMs. Unfortunately, it has been shown that an adversary with fine-tuning access to an LLM can bypass safeguards. Particularly…
The growing sophistication of modern malware and phishing campaigns has diminished the effectiveness of traditional signature-based intrusion detection systems. This work presents SecureScan, an AI-driven, triple-layer detection framework…
Existing research on LLM agent security mainly focuses on prompt injection and unsafe input/output behaviors. However, as agents increasingly rely on third-party tools and MCP servers, a new class of supply-chain threats has emerged, where…
LLM agents call tools, query databases, delegate tasks, and trigger external side effects. Once an agent system can act in the world, the question is no longer only whether harmful actions can be prevented--it is whether those actions…
Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that…
Skill libraries have become a practical way for LLM agents to reuse procedural experience across tasks. However, existing systems typically treat skills as flat, single-resolution prompt blocks. This creates a tension between relevance and…
Autonomous web agents are increasingly deployed for long-horizon tasks, yet their ability to adhere to real-world policies remains critically underexplored compared to standard safety objectives. To address this gap, we introduce…
Artificial intelligence is increasingly catalyzing scientific automation, with multimodal large language model (MLLM) agents evolving from lab assistants into self-driving lab operators. This transition imposes stringent safety requirements…
Random rules improve a coding agent's task performance as much as expert-curated ones (both $+13.8$pp on a discriminative subset of SWE-bench Verified), and in our data every individually beneficial rule is a negative constraint ("do not…
Agent skills, structured packages of procedural knowledge and executable resources that agents dynamically load at inference time, have become a reliable mechanism for augmenting LLM agents. Yet inference-time skill augmentation is…
Agentic applications powered by Large Language Models exhibit non-deterministic behaviors that can form hidden execution cycles, silently consuming resources without triggering explicit errors. Traditional observability platforms fail to…
Agents, language model-based systems capable of reasoning, planning, and acting are widely adopted in real-world tasks, yet how their performance changes as these systems scale across key dimensions remains underexplored. We introduce…
Recent advancements in Large Language Models (LLMs) have sparked interest in their application to Static Application Security Testing (SAST), primarily due to their superior contextual reasoning capabilities compared to traditional symbolic…
Large language models are increasingly deployed as autonomous agents for multi-step workflows in real-world software environments. However, existing agent benchmarks are limited by trajectory-opaque grading, underspecified safety and…
Vertical split learning (SL) enables collaborative model training across parties holding complementary features without sharing raw data, but recent work has shown that it is highly vulnerable to poisoning-based backdoor attacks operating…