Copertina

Comment and Control: Hijacking Agentic Workflows via Context-Grounded Evolution

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Fendley, Neil, Liu, Zhengyu, Guan, Aonan, Zhong, Jiacheng, Cao, Yinzhi
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Cryptography and Security Artificial Intelligence Software Engineering
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Detecting Privilege Escalation in Polyglot Microservices via Agentic Program Analysis
di: Li, Penghui, et al.
Pubblicazione: (2026)

Knowdit: Agentic Smart Contract Vulnerability Detection with Auditing Knowledge Summarization
di: Kong, Ziqiao, et al.
Pubblicazione: (2026)

SBOMs into Agentic AIBOMs: Schema Extensions, Agentic Orchestration, and Reproducibility Evaluation
di: Radanliev, Petar, et al.
Pubblicazione: (2026)

Towards Agentic Runtime Healing
di: Sun, Zhensu, et al.
Pubblicazione: (2024)

Locus: Agentic Predicate Synthesis for Directed Fuzzing
di: Zhu, Jie, et al.
Pubblicazione: (2025)

VULPO: Context-Aware Vulnerability Detection via On-Policy LLM Optimization
di: Li, Youpeng, et al.
Pubblicazione: (2025)

PoCo: Agentic Proof-of-Concept Exploit Generation for Smart Contracts
di: Andersson, Vivi, et al.
Pubblicazione: (2025)

CyberRAG: An Agentic RAG cyber attack classification and reporting tool
di: Blefari, Francesco, et al.
Pubblicazione: (2025)

MCPXKIT: The Unified Toolkit for Analyzing Model Context Protocol Security
di: Guo, Yongjian, et al.
Pubblicazione: (2025)

ContraFix: Agentic Vulnerability Repair via Differential Runtime Evidence and Skill Reuse
di: Liu, Simiao, et al.
Pubblicazione: (2026)

AEGIS: From Clues to Verdicts -- Graph-Guided Deep Vulnerability Reasoning via Dialectics and Meta-Auditing
di: Fang, Sen, et al.
Pubblicazione: (2026)

Data and Context Matter: Towards Generalizing AI-based Software Vulnerability Detection
di: Safdar, Rijha, et al.
Pubblicazione: (2025)

Automatic Red Teaming LLM-based Agents with Model Context Protocol Tools
di: He, Ping, et al.
Pubblicazione: (2025)

Learning to Generate Secure Code via Token-Level Rewards
di: Quan, Jiazheng, et al.
Pubblicazione: (2026)

Reflection-Driven Control for Trustworthy Code Agents
di: Wang, Bin, et al.
Pubblicazione: (2025)

EaTVul: ChatGPT-based Evasion Attack Against Software Vulnerability Detection
di: Liu, Shigang, et al.
Pubblicazione: (2024)

DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation
di: Huang, Li, et al.
Pubblicazione: (2026)

QLPro: Automated Code Vulnerability Discovery via LLM and Static Code Analysis Integration
di: Hu, Junze, et al.
Pubblicazione: (2025)

AgenticSCR: An Autonomous Agentic Secure Code Review for Immature Vulnerabilities Detection
di: Charoenwet, Wachiraphan, et al.
Pubblicazione: (2026)

Rethinking and Exploring String-Based Malware Family Classification in the Era of LLMs and RAG
di: Chen, Yufan, et al.
Pubblicazione: (2025)

LinuxArena: A Control Setting for AI Agents in Live Production Software Environments
di: Tracy, Tyler, et al.
Pubblicazione: (2026)

RefleXGen:The unexamined code is not worth using
di: Wang, Bin, et al.
Pubblicazione: (2025)

Detecting Trojaned DNNs via Spectral Regression Analysis
di: Pasini, Samuele, et al.
Pubblicazione: (2026)

Agentic Specification Generator for Move Programs
di: Fu, Yu-Fu, et al.
Pubblicazione: (2025)

KernelGPT: Enhanced Kernel Fuzzing via Large Language Models
di: Yang, Chenyuan, et al.
Pubblicazione: (2023)

MAVUL: Multi-Agent Vulnerability Detection via Contextual Reasoning and Interactive Refinement
di: Li, Youpeng, et al.
Pubblicazione: (2025)

Automatically Generating Rules of Malicious Software Packages via Large Language Model
di: Zhang, XiangRui, et al.
Pubblicazione: (2025)

Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning
di: Chu, Zhaoyang, et al.
Pubblicazione: (2025)

MalCodeAI: Autonomous Vulnerability Detection and Remediation via Language Agnostic Code Reasoning
di: Gajjar, Jugal, et al.
Pubblicazione: (2025)

Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning
di: Yan, Shenao, et al.
Pubblicazione: (2026)

CoDe-R: Refining Decompiler Output with LLMs via Rationale Guidance and Adaptive Inference
di: Zhang, Qiang, et al.
Pubblicazione: (2026)

Protect Your Secrets: Understanding and Measuring Data Exposure in VSCode Extensions
di: Liu, Yue, et al.
Pubblicazione: (2024)

Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications
di: Lu, Xiaoyue, et al.
Pubblicazione: (2026)

LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoning
di: Sun, Yuqiang, et al.
Pubblicazione: (2024)

GPTScan: Detecting Logic Vulnerabilities in Smart Contracts by Combining GPT with Program Analysis
di: Sun, Yuqiang, et al.
Pubblicazione: (2023)

Clawed and Dangerous: Can We Trust Open Agentic Systems?
di: Chen, Shiping, et al.
Pubblicazione: (2026)

Mirror Mirror on the Wall, Have I Forgotten it All? A New Framework for Evaluating Machine Unlearning
di: Brimhall, Brennon, et al.
Pubblicazione: (2025)

SecCodeBench-V2 Technical Report
di: Chen, Longfei, et al.
Pubblicazione: (2026)

Safety and Performance, Why Not Both? Bi-Objective Optimized Model Compression against Heterogeneous Attacks Toward AI Software Deployment
di: Zhu, Jie, et al.
Pubblicazione: (2024)

Investigating White-Box Attacks for On-Device Models
di: Zhou, Mingyi, et al.
Pubblicazione: (2024)