No article text was recorded for this version.
multi-strategy adversarial composition
Version 1 of 143 papers58 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning
- Blog: FuzzLLM: A Novel and Universal Fuzzing Framework for Proactively Discovering Jailbreak Vulnerabilities in Large Language Models
- Blog: Evaluating the Robustness of Multimodal Agents Against Active Environmental Injection Attacks
- Blog: Automated Generation of Multilingual Jailbreak Prompts
- Blog: AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration
- Blog: MAD-MAX: Modular And Diverse Malicious Attack MiXtures for Automated LLM Red Teaming
- Blog: Formalizing and Benchmarking Prompt Injection Attacks and Defenses
- Blog: Using Punctuation as an Adversarial Attack on Deep Learning-Based NLP Systems: An Empirical Study
- Blog: Exploiting Synergistic Cognitive Biases to Bypass Safety in LLMs
- Blog: Expanding Scope: Adapting English Adversarial Attacks to Chinese
- Blog: Raccoon: Prompt Extraction Benchmark of LLM-Integrated Applications
- Blog: Black-Box Adversarial Attacks on LLM-Based Code Completion
- Blog: CoP: Agentic Red-teaming for Large Language Models using Composition of Principles
- Blog: AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration
- Blog: On the Security Risks of Knowledge Graph Reasoning
- Blog: Automated testing for SQL injection vulnerabilities: an input mutation approach
- Blog: BELLS-O: Evaluating the Operational Trade-offs of LLM Supervision Systems
- Blog: MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents
- Blog: BlackboxBench: A Comprehensive Benchmark of Black-box Adversarial Attacks
- Blog: Plentiful Jailbreaks with String Compositions
- Blog: h4rm3l: A Language for Composable Jailbreak Attack Synthesis
- Blog: Functional Adversarial Attacks
- Blog: Jailbroken: How Does LLM Safety Training Fail?
- Blog: 'Do as I say not as I do': A Semi-Automated Approach for Jailbreak Prompt Attack against Multimodal LLMs
- Blog: The Unseen Adversaries: Robust and Generalized Defense Against Adversarial Patches
- Blog: Unrestricted Black-Box Adversarial Attack Using GAN with Limited Queries
- Blog: ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates
- Blog: A Tale of Evil Twins: Adversarial Inputs versus Poisoned Models
- Blog: StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusions
- Blog: Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks
- Blog: The Threat of PROMPTS in Large Language Models: A System and User Prompt Perspective
- Blog: CARBEN: Composite Adversarial Robustness Benchmark
- Blog: Monge blunts Bayes: Hardness Results for Adversarial Training.
- Blog: Protecting against simultaneous data poisoning attacks
- Blog: Improving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region Fitting
- Blog: AdvExpander: Generating Natural Language Adversarial Examples by Expanding Text
- Blog: Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets
- Blog: SecureSense: Defending Adversarial Attack for Secure Device-Free Human Activity Recognition
- Blog: Deciphering the Chaos: Enhancing Jailbreak Attacks via Adversarial Prompt Translation
- Blog: Semantically Stealthy Adversarial Attacks Against Segmentation Models
- Blog: WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
- Blog: Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks
- Blog: AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs
History & citation
Current · Permanent link
- This direction split from Synergistic Composition of Adversarial Strategies for LLM Jailbreaking (56% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_multi_strategy_adversarial_composition_40d14f4e,
title = {multi-strategy adversarial composition},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/multi-strategy-adversarial-composition/rdr_40d14f4e66374ba89a47073c3a7e1966},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_multi_strategy_adversarial_composition_40d14f4e_v1,
title = {multi-strategy adversarial composition},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/multi-strategy-adversarial-composition/rdr_40d14f4e66374ba89a47073c3a7e1966/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}