No article text was recorded for this version.
iterative prompt refinement (iterative adversarial refinement)
Version 2 of 2218 papers249 conceptsfrozen 2026-10-04
Papers in this version
- Blog: AutoRAN: Weak-to-Strong Jailbreaking of Large Reasoning Models
- Blog: CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent
- Blog: “Give a Positive Review Only”: An Early Investigation Into In-Paper Prompt Injection Attacks and Defenses for AI Reviewers
- Blog: Jailbreaking and Mitigation of Vulnerabilities in Large Language Models
- Blog: Automated Red Teaming with GOAT: the Generative Offensive Agent Tester
- Blog: SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning
- Blog: Red-teaming Activation Probes using Prompted LLMs
- Blog: NEXUS: Network Exploration for eXploiting Unsafe Sequences in Multi-Turn LLM Jailbreaks
- Blog: Fine-Grained Privacy Extraction from Retrieval-Augmented Generation Systems by Exploiting Knowledge Asymmetry
- Blog: Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling
- Blog: Defending Jailbreak Prompts via In-Context Adversarial Game
- Blog: AdaShield : Safeguarding Multimodal Large Language Models from Structure-Based Attack via Adaptive Shield Prompting
- Blog: Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities
- Blog: From Insight to Exploit: Leveraging LLM Collaboration for Adaptive Adversarial Text Generation
- Blog: Advancing Adversarial Suffix Transfer Learning on Aligned Large Language Models
- Blog: AutoAdv: Automated Adversarial Prompting for Multi-Turn Jailbreaking of Large Language Models
- Blog: CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent
- Blog: sudo rm -rf agentic_security
- Blog: Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks
- Blog: Proactive defense against LLM Jailbreak
- Blog: Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
- Blog: EVA: Red-Teaming GUI Agents via Evolving Indirect Prompt Injection
- Blog: TRUST-VLM: Thorough Red-Teaming for Uncovering Safety Threats in Vision-Language Models
- Blog: Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models
- Blog: Dynamic Risk Assessments for Offensive Cybersecurity Agents
- Blog: StruPhantom: Evolutionary Injection Attacks on Black-Box Tabular Agents Powered by Large Language Models
- Blog: SkillJect: Automating Stealthy Skill-Based Prompt Injection for Coding Agents with Trace-Driven Closed-Loop Refinement
- Blog: Jailbreaking Black Box Large Language Models in Twenty Queries
- Blog: "Give a Positive Review Only": An Early Investigation Into In-Paper Prompt Injection Attacks and Defenses for AI Reviewers
- Blog: DiffZOO: A Purely Query-Based Black-Box Attack for Red-teaming Text-to-Image Generative Model via Zeroth Order Optimization
- Blog: Prompt Injection attack against LLM-integrated Applications
- Blog: Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models
- Blog: GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
- Blog: FERRET: Framework for Expansion Reliant Red Teaming
- Blog: Locks Tested Without Burglars: Using Coding Assistants to Break Prompt Injection Defenses
- Blog: Defending Jailbreak Prompts via In-Context Adversarial Game
- Blog: CT-GAT: Cross-Task Generative Adversarial Attack based on Transferability
- Blog: Agent vs. Agent: Automated Data Generation and Red-Teaming for Custom Agentic Workflows
- Blog: Can Large Language Models Automatically Jailbreak GPT-4V?
- Blog: SHIELD: Defending Textual Neural Networks against Multiple Black-Box Adversarial Attacks with Stochastic Multi-Expert Patcher
- Blog: SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments
- Blog: PAR-AdvGAN: Improving Adversarial Attack Capability with Progressive Auto-regression AdvGAN
- Blog: Adversarial Style Augmentation via Large Language Model for Robust Fake News Detection
- Blog: Evil Geniuses: Delving into the Safety of LLM-based Agents
- Blog: On the Effectiveness of Adversarial Robustness for Abuse Mitigation with Counterspeech
- Blog: Uncovering the Vulnerability of Large Language Models in the Financial Domain via Risk Concealment
- Blog: Red-teaming Activation Probes using Prompted LLMs
- Blog: FLIRT: Feedback Loop In-context Red Teaming
- Blog: FoeGlass: Simple In-Context Learning Is Enough for Red Teaming Audio Deepfake Detectors
- Blog: Demonstrations of Integrity Attacks in Multi-Agent Systems
- Blog: Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation
- Blog: Attack Prompt Generation for Red Teaming and Defending Large Language Models
- Blog: Capability-Based Scaling Trends for LLM-Based Red-Teaming
- Blog: Red-Teaming LLM Multi-Agent Systems via Communication Attacks
- Blog: Jailbreaker: Automated Jailbreak Across Multiple Large Language Model Chatbots
- Blog: AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks
- Blog: Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models
- Blog: SoK: Large Language Model-Generated Textual Phishing Campaigns End-to-End Analysis of Generation, Characteristics, and Detection
- Blog: Crabs: Consuming Resrouce via Auto-generation for LLM-DoS Attack under Black-box Settings
- Blog: Comprehensive Assessment of Jailbreak Attacks Against LLMs
Showing 60 of 218 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_iterative_prompt_refinement_iterative_ad_eceb5c7e,
title = {iterative prompt refinement (iterative adversarial refinement)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/iterative-prompt-refinement-iterative-adversarial-refinement/rdr_eceb5c7eb294454fbad2622829335bda},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 2, frozen text):
@misc{lacuna_iterative_prompt_refinement_iterative_ad_eceb5c7e_v2,
title = {iterative prompt refinement (iterative adversarial refinement)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/iterative-prompt-refinement-iterative-adversarial-refinement/rdr_eceb5c7eb294454fbad2622829335bda/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}