paper-with-me

Papers

Query-Based Adversarial Prompt Generation

2024-02-19 · Jonathan Hayase, Ema Borevkovic, Nicholas Carlini, Florian Tramèr, Milad Nasr

Recent work has shown it is possible to construct adversarial examples that cause an aligned language model to emit harmful strings or perform harmful behavior. Existing attacks work either in the white-box setting (with full access to the model weights), or through transferability: the phenomenon that adversarial examples crafted on one model often remain effective on other models. We improve on prior work with a query-based attack that leverages API access to a remote language model to construct adversarial examples that cause the model to emit harmful strings with (much) higher probability than with transfer-only attacks. We validate our attack on GPT-3.5 and OpenAI's safety classifier; we can cause GPT-3.5 to emit harmful strings that current transfer attacks fail at, and we can evade the safety classifier with nearly 100% probability.

📄 PDF Abstract BibTeX arXiv:2402.12329

Code (2)

grayswanai/nanogcg pytorch
thompsonj/nanoGCG pytorch

Tasks

Language ModelingLanguage Modelling

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
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
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…
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…
{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…

Similar Papers 제목 키워드 기반

A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion

2023-03-29 · Haomin Zhuang, Yihua Zhang, Sijia Liu

Despite the record-breaking performance in Text-to-Image (T2I) generation by Stable Diffusion, less research attention is paid to its adversarial robustness. In this work, we study the problem of adversarial attack gener…

Adversarial AttackAdversarial RobustnessAdversarial Text

AutoRed: A Free-form Adversarial Prompt Generation Framework for Automated Red Teaming

2025-10-09 · Muxi Diao, Yutao Mou, Keqing He, Hanbo Song 외 arxiv

The safety of Large Language Models (LLMs) is crucial for the development of trustworthy AI applications. Existing red teaming methods often rely on seed instructions, which limits the semantic diversity of the synthesiz…

Red Teaming

AIP: Subverting Retrieval-Augmented Generation via Adversarial Instructional Prompt

2025-09-18 · Saket S. Chaturvedi, Gaurav Bagwe, Lan Zhang, Xiaoyong Yuan arxiv

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by retrieving relevant documents from external sources to improve factual accuracy and verifiability. However, this reliance introduces new attac…

Improved Generation of Adversarial Examples Against Safety-aligned LLMs

2024-05-28 · Qizhang Li, Yiwen Guo, WangMeng Zuo, Hao Chen

Adversarial prompts generated using gradient-based methods exhibit outstanding performance in performing automatic jailbreak attacks against safety-aligned LLMs. Nevertheless, due to the discrete nature of texts, the inp…

image-classificationImage Classification

Adversarial Threat Vectors and Risk Mitigation for Retrieval-Augmented Generation Systems

2025-05-30 · Chris M. Ward, Josh Harguess

Retrieval-Augmented Generation (RAG) systems, which integrate Large Language Models (LLMs) with external knowledge sources, are vulnerable to a range of adversarial attack vectors. This paper examines the importance of R…

Adversarial AttackData PoisoningManagementRAG+2