paper-with-me

Papers

Intention Analysis Makes LLMs A Good Jailbreak Defender

2024-01-12 · Yuqi Zhang, Liang Ding, Lefei Zhang, DaCheng Tao

Aligning large language models (LLMs) with human values, particularly when facing complex and stealthy jailbreak attacks, presents a formidable challenge. Unfortunately, existing methods often overlook this intrinsic nature of jailbreaks, which limits their effectiveness in such complex scenarios. In this study, we present a simple yet highly effective defense strategy, i.e., Intention Analysis ($\mathbb{IA}$). $\mathbb{IA}$ works by triggering LLMs' inherent self-correct and improve ability through a two-stage process: 1) analyzing the essential intention of the user input, and 2) providing final policy-aligned responses based on the first round conversation. Notably, $\mathbb{IA}$ is an inference-only method, thus could enhance LLM safety without compromising their helpfulness. Extensive experiments on varying jailbreak benchmarks across a wide range of LLMs show that $\mathbb{IA}$ could consistently and significantly reduce the harmfulness in responses (averagely -48.2% attack success rate). Encouragingly, with our $\mathbb{IA}$, Vicuna-7B even outperforms GPT-3.5 regarding attack success rate. We empirically demonstrate that, to some extent, $\mathbb{IA}$ is robust to errors in generated intentions. Further analyses reveal the underlying principle of $\mathbb{IA}$: suppressing LLM's tendency to follow jailbreak prompts, thereby enhancing safety.

📄 PDF Abstract BibTeX arXiv:2401.06561

Code (1)

alphadl/safellm_with_intentionanalysis 공식 구현

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 &…
{Dispute@FaQ-s}How to file a dispute with Expedia? How to file a dispute with Expedia? To file a complaint against Expedia, first try contacting their customer service directly. You can reach them by phone at…
Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
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…
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…

Similar Papers 제목 키워드 기반

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders

2025-05-30 · Yuqi Zhang, Yuchun Miao, Zuchao Li, Liang Ding

We introduce AMIA, a lightweight, inference-only defense for Large Vision-Language Models (LVLMs) that (1) Automatically Masks a small set of text-irrelevant image patches to disrupt adversarial perturbations, and (2) co…

Response Generation

Multilingual Jailbreak Challenges in Large Language Models

2023-10-10 · Yue Deng, Wenxuan Zhang, Sinno Jialin Pan, Lidong Bing

While large language models (LLMs) exhibit remarkable capabilities across a wide range of tasks, they pose potential safety concerns, such as the ``jailbreak'' problem, wherein malicious instructions can manipulate LLMs …

Machine Learning for Detection and Analysis of Novel LLM Jailbreaks

2025-10-02 · John Hawkins, Aditya Pramar, Rodney Beard, Rohitash Chandra arxiv

Large Language Models (LLMs) suffer from a range of vulnerabilities that allow malicious users to solicit undesirable responses through manipulation of the input text. These so-called jailbreak prompts are designed to tr…

Bidirectional Intention Inference Enhances LLMs' Defense Against Multi-Turn Jailbreak Attacks

2025-09-25 · Haibo Tong, Dongcheng Zhao, Guobin Shen, Xiang He 외 arxiv

The remarkable capabilities of Large Language Models (LLMs) have raised significant safety concerns, particularly regarding "jailbreak" attacks that exploit adversarial prompts to bypass safety alignment mechanisms. Exis…

JailbreakLens: Visual Analysis of Jailbreak Attacks Against Large Language Models

2024-04-12 · Yingchaojie Feng, Zhizhang Chen, Zhining Kang, Sijia Wang 외

The proliferation of large language models (LLMs) has underscored concerns regarding their security vulnerabilities, notably against jailbreak attacks, where adversaries design jailbreak prompts to circumvent safety mech…