arXiv AI
Jul 13
The Patchwork Problem in LLM-Generated Code
arXiv:2607. 08981v1 Announce Type: cross Abstract: LLM-generated code often compiles, passes tests, and appears correct, yet breaks once deployed.
Description-Code Inconsistency in Real-world MCP Servers: Measurement, Detection, and Security Implications
arXiv:2606. 04769v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) has emerged as a critical standard empowering Large Language Models (LLMs) to utilize external tools.
Related stories
arXiv AI
Jul 21
Is "Knowing It's Malicious Enough?" Evaluating LLMs for Fine-Grained Malware Behavior Auditing
arXiv:2509. 14335v2 Announce Type: replace-cross Abstract: Automated malware classifiers achieve strong detection performance, but auditing requires more than flagging a sample: analysts must explain malicious behaviors and justify them with code evidence.
arXiv AI
Jun 6
A Taxonomy of Runtime Faults in Model Context Protocol Servers
arXiv:2606. 05339v1 Announce Type: cross Abstract: MCP (Model Context Protocol) enables LLMs (Large Language Models) to interact with external tools and data sources via a standardized protocol.
arXiv AI
Jul 15
Bulkhead: Automated Semantic Detection and Remediation of Container Escape Vulnerabilities
arXiv:2607. 12723v1 Announce Type: cross Abstract: Filesystem isolation in container ecosystems is often weakened by cross-boundary path misresolution, causing path traversal (PaTra) vulnerabilities.
arXiv AI
Jul 15
Code-MUE: Measuring Code LLMs' Uncertainty through Execution-based Semantic Interaction Graphs
arXiv:2607. 12273v1 Announce Type: cross Abstract: As Code Large Language Models (LLMs) become central to modern software engineering, their inherent stochasticity poses significant real-world risks, where even minor errors can lead to severe functional, security, or safety consequences.
arXiv AI
Jul 2
Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces
arXiv:2607. 00481v1 Announce Type: cross Abstract: Jailbreak attacks remain a critical threat to the safe deployment of large language models (LLMs).
arXiv AI
Jul 1
A Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open Problems
arXiv:2606. 31639v1 Announce Type: cross Abstract: Large language models are no longer only text generators.
arXiv AI
Jul 8
Unicode TAG-Block Concealment of Tool-Metadata Payloads in the Model Context Protocol: An Approval-View Fidelity Gap Across Three Independent Server Implementations
arXiv:2607. 05744v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) is the dominant way coding agents discover and invoke external tools.
arXiv AI
Jul 28
Poster: Rethinking Security in LLM Code Generation through Real-World Risk Scenarios
arXiv:2607. 23088v1 Announce Type: cross Abstract: Large Language Models (LLMs) are widely used for code generation, yet their security behavior in realistic development workflows remains underexplored.
arXiv AI
Jun 18
SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents
arXiv:2606. 18356v1 Announce Type: cross Abstract: Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databases, or trigger harmful code and tool effects.
arXiv AI
Jun 18
Code-Augur: Agentic Vulnerability Detection via Specification Inference
arXiv:2606. 18619v1 Announce Type: cross Abstract: The advent of agentic vulnerability detection is already becoming a watershed moment for software security.
arXiv AI
Jun 9
Automated Framework to Evaluate and Harden LLM System Instructions against Encoding Attacks
arXiv:2604. 01039v2 Announce Type: replace-cross Abstract: System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications.