arXiv AI

AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy Mitigation

The paper examines how Large Language Models (LLMs) have introduced a trustworthiness crisis in cybersecurity vulnerability assessment, producing artifacts known as "AI slop" such as hallucinated vulnerabilities and incorrect patches. It presents a taxonomy of these failures, attributes them to a mismatch between deductive reasoning and probabilistic generation, and introduces the Deductive Coverage Score as a measurable proxy. The authors review mitigation strategies, critique passive approaches, and propose active neuro‑symbolic verification, concluding with new evaluation tools—CVE‑Bench and Slop‑Score—to shift focus from linguistic fluency to mathematical verifiability.

arXiv AI

Sep 12

Architecting the Secure AI-SOC: A Neurosymbolic Framework for Pipeline Integrity and Threat Mitigation

The paper proposes a neurosymbolic defense architecture for AI-enhanced Security Operations Centers (AI‑SOCs) that protects against indirect prompt injection via log poisoning. It combines deterministic SIEM decoders as a pre‑filter with NeMo Guardrails for semantic validation, and adds a closed‑loop telemetry system for Human‑in‑the‑Loop visibility. Experimental results mapped to the MITRE ATLAS taxonomy show the approach effectively dismantles promptware kill chains and delivers a resilient, observable defense for next‑generation AI‑SOCs.

By Anna Gazani, Spyridon Kounoupidis, Panagiotis Katsaros, Nikolaos Kekatos, Grigorios Tsoumakas, Georgios Koutidis

llms rag safety

arXiv AI

Sep 15

Automating Attack Graph Construction for Agentic Pentesting. Towards Neuro-Symbolic Vulnerability Hunting

arXiv:2609.15523v1 Announce Type: cross Abstract: Logic attack graphs grounded in scanner output provide explicit and auditable attack path reasoning LLM-based agents lack. Integrating symbolic frame...

By Oliver Stevanovic, Jasmin Wachter

llms agents

arXiv AI

Sep 15

Trustworthy Agentic AI: A Comprehensive Cybersecurity and Systems Survey on Threat Landscapes, Defense Architectures, and Open Challenges

arXiv:2609.13731v1 Announce Type: new Abstract: The transition from passive foundation models to autonomous, goal-directed agentic AI systems has introduced unprecedented capabilities by coupling rec...

By Seyedakbar Mostafavi

llms agents benchmarks safety

arXiv AI

Jul 9

Large Language Models (LLMs) and Generative AI in Cybersecurity and Privacy: A Survey of Dual-Use Risks, AI-Generated Malware, Explainability, and Defensive Strategies

arXiv:2607. 06963v1 Announce Type: cross Abstract: Large Language Models (LLMs) and generative AI (GenAI) systems, such as ChatGPT, Claude, Gemini, LLaMA, Copilot, Stable Diffusion by OpenAI, Anthropic, Google, Meta, Microsoft, Stability AI, respectively, are revolutionizing cybersecurity, enabling both automated defense and sophisticated attacks.

By Kiarash Ahi, Saeed Valizadeh

llms diffusion benchmarks safety

arXiv AI

Jun 12

The Emergence of Autonomous Penetration Capabilities in Large Language Model-Powered AI Systems

arXiv:2606. 13079v1 Announce Type: cross Abstract: Nowadays, the autonomous execution of cyberattacks capable of causing substantial real-world harm is widely regarded as one of the critical red lines that frontier AI systems must not cross.

By Jiaqi Luo, Jiarun Dai, Zhile Chen, Jia Xu, Weibing Wang, Yawen Duan, Brian Tse, Geng Hong, Xudong Pan, Yuan Zhang, Min Yang

llms agents safety

arXiv AI

Jun 24

FALCON: Transforming Cyber Threat Intelligence into Deployable IDS Rules with Self-Reflection

arXiv:2508. 18684v2 Announce Type: replace-cross Abstract: Signature-based Intrusion Detection Systems (IDS) detect malicious activity by matching network or host events against predefined rules.

By Shaswata Mitra, Subash Neupane, Martin Duclos, Sudip Mittal, Aritran Piplai, Md Rayhanur Rahman, Edward Zieglar, Shahram Rahimi

llms rag agents safety

Hugging Face Trending Papers

Jul 8

Large Language Models (LLMs) and Generative AI in Cybersecurity and Privacy: A Survey of Dual-Use Risks, AI-Generated Malware, Explainability, and Defensive Strategies

Large Language Models (LLMs) and generative AI (GenAI) systems, such as ChatGPT, Claude, Gemini, LLaMA, Copilot, Stable Diffusion by OpenAI, Anthropic, Google, Meta, Microsoft, Stability AI, respectively, are revolutionizing cybersecurity, enabling both automated defense and sophisticated attacks. These technologies power real-time threat detection, phishing defense, secure code generation, and vulnerability exploitation at unprecedented scales.

llms diffusion benchmarks safety

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.

By Zhengxiong Luo, Mehtab Zafar, Dylan Wolff, Abhik Roychoudhury

llms agents benchmarks

arXiv AI

Jul 7

Don't Make Models Guess Security and Safety: Symbolic Guardrails for Domain-Specific AI Agents

arXiv:2604. 15579v2 Announce Type: replace-cross Abstract: There is increasing interest in integrating AI agents that invoke tools into domain-specific commercial software, where unintended tool calls can cause serious security and safety incidents.

By Yining Hong, Yining She, Eunsuk Kang, Christopher S. Timperley, Christian K\"astner

agents benchmarks safety

arXiv Computation and Language

Aug 25

CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild

arXiv:2608.23181v1 Announce Type: cross Abstract: As large language models (LLMs) continue to advance in coding capabilities, their potential in cybersecurity has drawn increasing research attention,...

By Jian Yang, Haau-Sing Li, Shawn Guo, Zixi Zhao, Yibo Tan, Jiajun Wu, Aishan Liu, Xianglong Liu, Tianyu Zheng, Bryan Dai, Chengran Yang

llms agents nlp

arXiv AI

Oct 5

CVE2AP: Automated Generation of PDDL-Encoded Attack Paths via Large Language Models

CVE2AP is an LLM-based system that automatically converts natural language CVE descriptions into PDDL-encoded attack paths. It uses structured prompting and an error‑feedback loop that refines outputs based on planner‑reported syntactic and solvability errors. Empirical tests across various LLMs show high quality results, with up to 86.9% syntax correctness, 78.6% solvability, and 93.1% semantic correctness, and GPT‑5.5 providing the best quality‑cost balance.

By Lin Cui, Vincenzo Scotti, Raffaela Mirandola

llms

arXiv AI

Jun 12

Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents

arXiv:2606. 13385v1 Announce Type: cross Abstract: Web agents driven by large language models (LLMs) are increasingly deployed in real-world environments, where they operate over untrusted web content and execute actions with direct consequences.

By Zihao Wang, Yiming Li, Yutong Wu, Zheyu Liu, Kangjie Chen, Fok Kar Wai, Pin-Yu Chen, Vrizlynn L. L. Thing, Bo Li, Dacheng Tao, Tianwei Zhang

llms agents benchmarks safety

Related stories