Related papers: Execution Is the New Attack Surface: Survivability…
AI agents dynamically acquire tools, orchestrate sub-agents, and transact across organizational boundaries, yet no existing security layer verifies what an agent can do, whether it executed what it claims, or what happened in a multi-agent…
We present enclawed, a hard-fork hardening framework built on the OpenClaw AI assistant gateway. enclawed targets deployments that need attestable peer trust, deny-by-default external connectivity, signed-module loading, and a…
The safety of autonomous AI agents is increasingly recognized as a critical open problem. As agents transition from passive text generators to active actors capable of executing shell commands, modifying files, calling APIs, and browsing…
Self-supervised learning (SSL) is the latest breakthrough in speech processing, especially for label-scarce downstream tasks by leveraging massive unlabeled audio data. The noise robustness of the SSL is one of the important challenges to…
Large language model (LLM) agents are increasingly applied to network troubleshooting, but root-cause localization on public benchmarks remains well below practical deployment thresholds. We argue this is because existing agents do not…
We consider the formulation of a symbolic execution (SE) procedure for functional programs that interact with effectful, opaque libraries. Our procedure allows specifications of libraries and abstract data type (ADT) methods that are…
Soft actor-critic (SAC) in reinforcement learning is expected to be one of the next-generation robot control schemes. Its ability to maximize policy entropy would make a robotic controller robust to noise and perturbation, which is useful…
LLM agents increasingly operate in open-ended environments spanning hundreds of sequential episodes, yet they remain largely stateless: each task is solved from scratch without converting past experience into better future behavior. The…
Trusted Execution Environments (TEEs) have been proposed as a solution to protect code confidentiality in scenarios where computation is outsourced to an untrusted operator. We study the resilience of such solutions to side-channel attacks…
Autonomous coding agents are increasingly integrated into software development workflows, offering capabilities that extend beyond code suggestion to active system interaction and environment management. OpenClaw, a representative platform…
Prediction markets offer a natural testbed for trading agents: contracts have binary payoffs, prices can be interpreted as probabilities, and realized performance depends critically on market microstructure, fees, and settlement risk. We…
Large Language Models deployed as code generation agents exhibit stochastic behavior incompatible with the deterministic guarantees required by software engineering. We formalize the Dual-State Action Pair (DSAP), an execution primitive…
Black-box textual adversarial attacks are challenging due to the lack of model information and the discrete, non-differentiable nature of text. Existing methods often lack versatility for attacking different models, suffer from limited…
Tool-augmented LLM agents introduce security risks that extend beyond user-input filtering, including indirect prompt injection through fetched content, unsafe tool execution, credential leakage, and tampering with local control files. We…
Tool-using LLM agents fail through trajectories rather than only final responses, as they may execute unsafe tool calls, follow injected instructions, comply with harmful requests, or over-refuse benign tasks despite producing a seemingly…
Mobile Edge Computing (MEC) refers to the concept of placing computational capability and applications at the edge of the network, providing benefits such as reduced latency in handling client requests, reduced network congestion, and…
As Large Language Models are rapidly deployed across diverse applications from healthcare to financial advice, safety evaluation struggles to keep pace. Current benchmarks focus on single-turn interactions with generic policies, failing to…
Ensuring functional safety in human-robot interaction is challenging because AI perception is inherently probabilistic, whereas industrial standards require deterministic behavior. We present an LLM-guided safety agent for edge robotics,…
Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocols such as MCP and A2A, introduce a threat surface that differs materially from standalone…
The rise of AI agent frameworks has introduced agent skills, modular packages containing instructions and executable code that dynamically extend agent capabilities. While this architecture enables powerful customization, skills execute…