Scope-Gap Injection: Exploiting Evaluator Channel Blind Spots in the OpenClaw Agent Security Competition
This paper introduces Scope-Gap Injection (SGI), an indirect prompt injection method for multi-stage LLM-agent safety pi
#cs.AI
共收录 1652 条相关情报。
← 返回所有主题From Speech Tokens to Stolen Voices: Attacker-Chosen-Text Speaker Impersonation via Representation Inversion
Speech interaction systems have gradually evolved from traditional cascaded systems that use text as intermediate inform
LLM WikiLeaks: Uncovering URL-Based Capability Extension and Security Circumvention in Agentic Message Boards
Autonomous agents have been observed acting beyond their assigned tasks, accessing unauthorized systems, and establishin
SentryBench: A Cost-Sensitive Benchmark for Adversarial Robustness of Tool-Using LLM Agents in Public-Safety Deployments
Large language model (LLM) agents are increasingly wired to consequential tools that send public alerts, dispatch respon
CyberDual: AI Attackers versus AI Code Reviewers in Real Software Maintenance
Open-source projects now let AI agents review incoming code, but the code under review may itself come from an AI attack
Repairing Broken Access Control in Web Applications with LLMs: An Empirical Benchmark Study
Broken access control (BAC) ranks among the most severe web-application vulnerability classes, yet its automated repair
NameTrap: Steering AI Coding Agents Toward Security Vulnerabilities via Variable Names
AI coding agents routinely clone repositories, install packages, and read source code obtained from the Web, so publicly
Trust Mechanisms for Offline Generative AI at the Edge: A Connectivity-Regime Framework and an Empirical Study on a Raspberry Pi 5
Generative AI and large language models (LLMs) are moving into the Internet of Things, yet most deployments assume cloud
Extraction meets Distillation - cryptanalytic techniques to recover parameters from a Deep Neural Network
We study fully connected neural-network reconstruction by combining cryptanalytic weight-direction extraction with learn
ProbeID: Verifying MCP Tool Identity for LLM Agents under Registry Drift
Agents select tools by copyable descriptions, which cannot establish which implementation runs. ProbeID compares canonic
Pacifo: An Efficient Fully Homomorphic Encryption-based Lightweight ResNet for Trustworthy Machine Learning as a Service
Machine Learning as a Service (MLaaS) has become a popular paradigm for deploying AI applications. However, it raises si
Can Agentic Code Review Catch Vulnerabilities Before They Are Merged?
LLM agents have been increasingly adopted for security-focused code review, but existing benchmarks mostly derive the re
From Hype to ROI: An Economic Model for LLM Adoption in Information Systems and Security Operations
Large Language Models (LLMs) promise significant efficiency gains across information-intensive operations by automating
A Deterministic Security Runtime for LLM Agents on MPI and Batch-Scheduled HPC Systems: Consensus-Governed, Hardware-Rooted Supervision of Every Rank
Large language model agents launch simulations on high-performance computing (HPC) systems, where one sbatch or mpirun c
Beyond Copying: Lifelong Smart Contract Security Task Construction via Protocol Mutation
AI agents can inspect code and run tests to support smart contract security. SlowMist reports about $38.6 billion in los
Data-Efficient Backdoor Attacks on Code Models via Trigger-Neutralized Counterfactual Scoring
Pre-trained code models are exposed to backdoor poisoning, in which crafted training samples make the model misbehave on
AgentTrace: Execution-Level Fingerprinting of Black-Box LLM Agents
Verifying the provenance of autonomous LLM agents is a critical security challenge. Existing semantic attribution is eas
Concept Acupuncturist: An Efficient and Precise Concept Erasure Method for Diffusion Models via Sparse Autoencoders
Diffusion-based image generation models produce high-quality images but may generate harmful or policy-violating content
Agentic AI Defense: Decode-Time Provenance Binding for MCP
Agentic AI systems using the Model Context Protocol (MCP) are vulnerable to indirect prompt injection through untrusted
Social-HUMINT: An LLM-Augmented Unified Framework for Measuring Social Media Exposure
In the post-API landscape, social-media profiling has become inexpensive and automated: Large Language Models (LLMs) can