paper-with-me

Papers

AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

2024-04-11 · Zeyi Liao, Huan Sun

As large language models (LLMs) become increasingly prevalent and integrated into autonomous systems, ensuring their safety is imperative. Despite significant strides toward safety alignment, recent work GCG~\citep{zou2023universal} proposes a discrete token optimization algorithm and selects the single suffix with the lowest loss to successfully jailbreak aligned LLMs. In this work, we first discuss the drawbacks of solely picking the suffix with the lowest loss during GCG optimization for jailbreaking and uncover the missed successful suffixes during the intermediate steps. Moreover, we utilize those successful suffixes as training data to learn a generative model, named AmpleGCG, which captures the distribution of adversarial suffixes given a harmful query and enables the rapid generation of hundreds of suffixes for any harmful queries in seconds. AmpleGCG achieves near 100\% attack success rate (ASR) on two aligned LLMs (Llama-2-7B-chat and Vicuna-7B), surpassing two strongest attack baselines. More interestingly, AmpleGCG also transfers seamlessly to attack different models, including closed-source LLMs, achieving a 99\% ASR on the latest GPT-3.5. To summarize, our work amplifies the impact of GCG by training a generative model of adversarial suffixes that is universal to any harmful queries and transferable from attacking open-source LLMs to closed-source LLMs. In addition, it can generate 200 adversarial suffixes for one harmful query in only 4 seconds, rendering it more challenging to defend.

📄 PDF Abstract BibTeX arXiv:2404.07921

Code (1)

osu-nlp-group/amplegcg 공식 구현 pytorch

Tasks

Safety Alignment

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
15 Ways to Contact How can i speak to someone at Delta Airlines 설명 없음
Attention 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…

Similar Papers 제목 키워드 기반

AmpleGCG-Plus: A Strong Generative Model of Adversarial Suffixes to Jailbreak LLMs with Higher Success Rates in Fewer Attempts

2024-10-29 · Vishal Kumar, Zeyi Liao, Jaylen Jones, Huan Sun

Although large language models (LLMs) are typically aligned, they remain vulnerable to jailbreaking through either carefully crafted prompts in natural language or, interestingly, gibberish adversarial suffixes. However,…

Universal and Transferable Adversarial Attack on Large Language Models Using Exponentiated Gradient Descent

2025-08-20 · Sajib Biswas, Mao Nishino, Samuel Jacob Chacko, Xiuwen Liu arxiv

As large language models (LLMs) are increasingly deployed in critical applications, ensuring their robustness and safety alignment remains a major challenge. Despite the overall success of alignment techniques such as re…

Reinforcement LearningAdversarial Attack

Universal Adversarial Suffixes for Language Models Using Reinforcement Learning with Calibrated Reward

2025-12-09 · Sampriti Soor, Suklav Ghosh, Arijit Sur arxiv

Language models are vulnerable to short adversarial suffixes that can reliably alter predictions. Previous works usually find such suffixes with gradient search or rule-based methods, but these are brittle and often tied…

Natural Language InferenceReinforcement Learning

ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings

2024-02-25 · Hao Wang, Hao Li, Minlie Huang, Lei Sha

The safety defense methods of Large language models(LLMs) stays limited because the dangerous prompts are manually curated to just few known attack types, which fails to keep pace with emerging varieties. Recent studies …

Language ModellingLarge Language Model

Alignment Under Pressure: The Case for Informed Adversaries When Evaluating LLM Defenses

2025-05-21 · Xiaoxue Yang, Bozhidar Stevanoski, Matthieu Meeus, Yves-Alexandre de Montjoye

Large language models (LLMs) are rapidly deployed in real-world applications ranging from chatbots to agentic systems. Alignment is one of the main approaches used to defend against attacks such as prompt injection and j…