# AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation

arXiv: https://arxiv.org/abs/2410.09040 · HTML: https://mlsanity.com/paper/2410.09040/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- Builds on 31 of its 39 references that are in the map.
- First posted on arXiv 11 Oct 2024.

## Placed in

- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [Tree of Attacks: Jailbreaking Black-Box LLMs Automatically](https://mlsanity.com/paper/2312.02119/) (2023)
- [How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs](https://mlsanity.com/paper/2401.06373/) (2024)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks](https://mlsanity.com/paper/2404.02151/) (2024)
- [Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations](https://mlsanity.com/paper/2310.06387/) (2023)
- [GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher](https://mlsanity.com/paper/2308.06463/) (2023)
- [Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation](https://mlsanity.com/paper/2311.03348/) (2023)
- [MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots](https://mlsanity.com/paper/2307.08715/) (2023)
- [AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs](https://mlsanity.com/paper/2404.07921/) (2024)
- [Open Sesame! Universal Black Box Jailbreaking of Large Language Models](https://mlsanity.com/paper/2309.01446/) (2023)
- [AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models](https://mlsanity.com/paper/2310.15140/) (2023)
- [How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs](https://mlsanity.com/paper/2311.16101/) (2023)
- [Attacking Large Language Models with Projected Gradient Descent](https://mlsanity.com/paper/2402.09154/) (2024)
- [Attention-Enhancing Backdoor Attacks Against BERT-based Models](https://mlsanity.com/paper/2310.14480/) (2023)
- [All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks](https://mlsanity.com/paper/2401.09798/) (2024)
- [Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics](https://mlsanity.com/paper/2309.07120/) (2023)

## Built on by (most cited first, 30 of 33)

- [A Survey on Trustworthy LLM Agents: Threats and Countermeasures](https://mlsanity.com/paper/2503.09648/) (2025)
- [STAR-1: Safer Alignment of Reasoning LLMs with 1K Data](https://mlsanity.com/paper/2504.01903/) (2025)
- [Large Language Model Safety: A Holistic Survey](https://mlsanity.com/paper/2412.17686/) (2024)
- [AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents](https://mlsanity.com/paper/2509.07764/) (2025)
- [Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models](https://mlsanity.com/paper/2412.08615/) (2024)
- [May I have your Attention? Breaking Fine-Tuning based Prompt Injection Defenses using Architecture-Aware Attacks](https://mlsanity.com/paper/2507.07417/) (2025)
- [D-Fusion: Direct Preference Optimization for Aligning Diffusion Models with Visually Consistent Samples](https://mlsanity.com/paper/2505.22002/) (2025)
- [Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints](https://mlsanity.com/paper/2503.01865/) (2025)
- [Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models](https://mlsanity.com/paper/2503.06269/) (2025)
- [Universal Jailbreak Suffixes Are Strong Attention Hijackers](https://mlsanity.com/paper/2506.12880/) (2025)
- [HoneyTrap: Deceiving Large Language Model Attackers to Honeypot Traps with Resilient Multi-Agent Defense](https://mlsanity.com/paper/2601.04034/) (2026)
- [RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs](https://mlsanity.com/paper/2605.02946/) (2026)
- [Model-Editing-Based Jailbreak against Safety-aligned Large Language Models](https://mlsanity.com/paper/2412.08201/) (2024)
- [When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs](https://mlsanity.com/paper/2508.03365/) (2025)
- [ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments](https://mlsanity.com/paper/2508.04204/) (2025)
- [On Surjectivity of Neural Networks: Can you elicit any behavior from your model?](https://mlsanity.com/paper/2508.19445/) (2025)
- [Safer by Diffusion, Broken by Context: Diffusion LLM's Safety Blessing and Its Failure Mode](https://mlsanity.com/paper/2602.00388/) (2026)
- [Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models](https://mlsanity.com/paper/2602.01025/) (2026)
- [Adversarial Attacks on Multimodal Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2603.27918/) (2026)
- [Preventing Jailbreak Prompts as Malicious Tools for Cybercriminals: A Cyber Defense Perspective](https://mlsanity.com/paper/2411.16642/) (2024)
- [NonTextual Target Attack](https://mlsanity.com/paper/2510.02999/) (2025)
- [Checkpoint-GCG: Auditing and Attacking Fine-Tuning-Based Prompt Injection Defenses](https://mlsanity.com/paper/2505.15738/) (2025)
- [Breaking MCP with Function Hijacking Attacks: Novel Threats for Function Calling and Agentic Models](https://mlsanity.com/paper/2604.20994/) (2026)
- [SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks](https://mlsanity.com/paper/2606.05609/) (2026)
- [Benign-to-Toxic Jailbreaking: Inducing Harmful Responses from Harmless Prompts](https://mlsanity.com/paper/2505.21556/) (2025)
- [Eyes-on-Me: Scalable RAG Poisoning through Transferable Attention-Steering Attractors](https://mlsanity.com/paper/2510.00586/) (2025)
- [SoundBreak: A Systematic Study of Audio-Only Adversarial Attacks on Trimodal Models](https://mlsanity.com/paper/2601.16231/) (2026)
- [Sirens' Whisper: Inaudible Near-Ultrasonic Jailbreaks of Speech-Driven LLMs](https://mlsanity.com/paper/2603.13847/) (2026)
- [SafeBehavior: Simulating Human-Like Multistage Reasoning to Mitigate Jailbreak Attacks in Large Language Models](https://mlsanity.com/paper/2509.26345/) (2025)
- [Distillability of LLM Security Logic: Predicting Attack Success Rate of Outline Filling Attack via Ranking Regression](https://mlsanity.com/paper/2511.22044/) (2025)

## Abstract (arXiv)

This paper studies the vulnerabilities of transformer-based Large Language Models (LLMs) to jailbreaking attacks, focusing specifically on the optimization-based Greedy Coordinate Gradient (GCG) strategy. We first observe a positive correlation between the effectiveness of attacks and the internal behaviors of the models. For instance, attacks tend to be less effective when models pay more attention to system prompts designed to ensure LLM safety alignment. Building on this discovery, we introduce an enhanced method that manipulates models' attention scores to facilitate LLM jailbreaking, which we term AttnGCG. Empirically, AttnGCG shows consistent improvements in attack efficacy across diverse LLMs, achieving an average increase of ~7% in the Llama-2 series and ~10% in the Gemma series. Our strategy also demonstrates robust attack transferability against both unseen harmful goals and black-box LLMs like GPT-3.5 and GPT-4. Moreover, we note our attention-score visualization is more interpretable, allowing us to gain better insights into how our targeted attention manipulation facilitates more effective jailbreaking. We release the code at https://github.com/UCSC-VLAA/AttnGCG-attack.