Related papers: Clawdrain: Exploiting Tool-Calling Chains for Stea…

Deep neural networks are known to have security issues. One particular threat is the Trojan attack. It occurs when the attackers stealthily manipulate the model's behavior through Trojaned training samples, which can later be exploited.…

Pre-trained vision models (PVMs) have become a dominant component due to their exceptional performance when fine-tuned for downstream tasks. However, the presence of backdoors within PVMs poses significant threats. Unfortunately, existing…

High-privilege LLM agents that autonomously process external documentation are increasingly trusted to automate tasks by reading and executing project instructions, yet they are granted terminal access, filesystem control, and outbound…

Tool-enabled AI agents are increasingly deployed in cloud-hosted environments and offered as services, where they perform side-effecting operations through privileged tools within execution environments. While such agents enable powerful…

Multi-agent AI systems have proven effective for complex reasoning. These systems are compounded by specialized agents, which collaborate through explicit communication, but incur substantial computational overhead. A natural question…

LLM-based agent systems increasingly rely on agent skills sourced from open registries to extend their capabilities, yet the openness of such ecosystems makes skills difficult to thoroughly vet. Existing attacks rely on injecting malicious…

Autonomous AI agents extend large language models into full runtime systems that load skills, ingest external content, maintain memory, plan multi-step actions, and invoke privileged tools. In such systems, security failures rarely remain…

Every LLM tool call is structurally an RPC -- a function name, JSON arguments, and a serialized result -- yet each protocol (native Python, MCP, OpenAPI, LangChain) is integrated from scratch. We present ToolRegistry, a system that makes…

The increasing prevalence of Large Language Models (LMs) in critical applications highlights the need for controlled language generation strategies that are not only computationally efficient but that also enjoy performance guarantees. To…

Deep neural networks have demonstrated remarkable success across numerous tasks, yet they remain vulnerable to Trojan (backdoor) attacks, raising serious concerns about their safety in real-world mission-critical applications. A common…

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…

Truncation is widely used in generative models for improving the quality of the generated samples, at the expense of reducing their diversity. We propose to leverage the StyleGAN generative architecture to devise a new truncation technique,…

Large language models (LLMs) are increasingly deployed in agentic systems, where a fundamental task is mapping user intents to relevant external tools. Errors in tool selection can have severe outcomes, such as unauthorized data access,…

Large language model (LLM) agents increasingly rely on reusable skills: capability packages that combine instructions, control flow, constraints, and tool calls. In current agent systems, however, skills are still represented by text-heavy…

A globally distributed IC supply chain brings risks due to untrusted third parties. The risks span inadvertent use of hardware Trojan (HT), inserted Intellectual Property (3P-IP) or Electronic Design Automation (EDA) flows. HT can introduce…

This paper proposes MergeGuard, a novel methodology for mitigation of AI Trojan attacks. Trojan attacks on AI models cause inputs embedded with triggers to be misclassified to an adversary's target class, posing a significant threat to…

Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs. Existing approaches overwhelmingly operate within the prompt-optimization paradigm: whether through traditional…

Autonomous web agents such as \textbf{OpenClaw} are rapidly moving into high-impact real-world workflows, but their security robustness under live network threats remains insufficiently evaluated. Existing benchmarks mainly focus on static…

As Large Language Models (LLMs) become integral to computing infrastructure, safety alignment serves as the primary security control preventing the generation of harmful payloads. However, this defense remains brittle. Existing jailbreak…

Large Language Model (LLM) agents are autonomous systems powered by LLMs, capable of reasoning and planning to solve problems by leveraging a set of tools. However, the integration of multi-tool capabilities in LLM agents introduces…