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

Backdoor (trojan) attacks embed hidden, controllable behaviors into machine-learning models so that models behave normally on benign inputs but produce attacker-chosen outputs when a trigger is present. This survey reviews the rapidly…

Driven by Large Language Models, the single-agent, multi-tool architecture has become a popular paradigm for autonomous agents. However, this architecture introduces a severe privacy risk, which we term Tools Orchestration Privacy Risk…

While LLM-based agents can interact with environments via invoking external tools, their expanded capabilities also amplify security risks. Monitoring step-level tool invocation behaviors in real time and proactively intervening before…

Autonomous AI agents live or die by the API tokens they consume: without paid inference capacity they cannot reason, act, or delegate. Compute-token cost has become the binding resource of the emerging agent economy, yet it is…

Deep reinforcement learning (DRL) has achieved remarkable success in a wide range of sequential decision-making applications, including robotics, healthcare, smart grids, and finance. Recent studies reveal that adversaries can implant…

Autonomous AI agents powered by large language models (LLMs) with structured function-calling interfaces enable real-time data retrieval, computation, and multi-step orchestration. However, the rapid growth of plugins, connectors, and…

Autonomous agents powered by large language models introduce a class of execution-layer vulnerabilities -- prompt injection, retrieval poisoning, and uncontrolled tool invocation -- that existing guardrails fail to address systematically.…

Machine learning models that use deep neural networks (DNNs) are vulnerable to backdoor attacks. An adversary carrying out a backdoor attack embeds a predefined perturbation called a trigger into a small subset of input samples and trains…

Translating statistical methods into reliable software is a persistent bottleneck in quantitative research. Existing AI code-generation tools produce code quickly but cannot guarantee faithful implementation -- a critical requirement for…

In this paper, we investigate the advanced circuit features such as wordline- (WL) underdrive (prevents retention failure) and overdrive (assists write) employed in the peripherals of Dynamic RAM (DRAM) memories from a security perspective.…

Third-party skills extend LLM agents with powerful capabilities but often handle sensitive credentials in privileged environments, making leakage risks poorly understood. We present the first large-scale empirical study of this problem,…

Every agent interaction generates a next-state signal, namely the user reply, tool output, terminal or GUI state change that follows each action, yet no existing agentic RL system recovers it as a live, online learning source. We present…

Trojan (backdoor) attack is a form of adversarial attack on deep neural networks where the attacker provides victims with a model trained/retrained on malicious data. The backdoor can be activated when a normal input is stamped with a…

As autonomous agents (e.g., OpenClaw) increasingly operate with deep system-level privileges to execute complex tasks, they introduce severe, unmitigated security risks. Current vulnerability analyses overwhelmingly focus on single-turn,…

Agent skills extend local AI agents, such as Claude Code or Open Claw, with additional functionality, and their popularity has led to the emergence of dedicated skill marketplaces, similar to app stores for mobile applications.…

Enabling continual learning in LLMs remains a key unresolved research challenge. In a recent announcement, a frontier LLM company made a step towards this by introducing Agent Skills, a framework that equips agents with new knowledge based…

Secure elements physically exposed to adversaries are frequently targeted by fault attacks. These attacks can be utilized to hijack the control-flow of software allowing the attacker to bypass security measures, extract sensitive data, or…

Federated Learning (FL) is a promising approach enabling multiple clients to train Deep Neural Networks (DNNs) collaboratively without sharing their local training data. However, FL is susceptible to backdoor (or targeted poisoning)…

Self-supervised learning (SSL) methods have resulted in broad improvements to neural network performance by leveraging large, untapped collections of unlabeled data to learn generalized underlying structure. In this work, we harness…

Skill ecosystems have emerged as an increasingly important layer in Large Language Model (LLM) agent systems, enabling reusable task packaging, public distribution, and community-driven capability sharing. However, despite their rapid…