Large Language Models are Vulnerable to Bait-and-Switch Attacks for Generating Harmful Content

• URL: http://arxiv.org/abs/2402.13926v1
• Date: Wed, 21 Feb 2024 16:46:36 GMT
• Title: Large Language Models are Vulnerable to Bait-and-Switch Attacks for Generating Harmful Content
• Authors: Federico Bianchi, James Zou
• Abstract summary: Even safe text coming from large language models can be turned into potentially dangerous content through Bait-and-Switch attacks. The alarming efficacy of this approach highlights a significant challenge in developing reliable safety guardrails for LLMs.
• Score: 33.99403318079253
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The risks derived from large language models (LLMs) generating deceptive and damaging content have been the subject of considerable research, but even safe generations can lead to problematic downstream impacts. In our study, we shift the focus to how even safe text coming from LLMs can be easily turned into potentially dangerous content through Bait-and-Switch attacks. In such attacks, the user first prompts LLMs with safe questions and then employs a simple find-and-replace post-hoc technique to manipulate the outputs into harmful narratives. The alarming efficacy of this approach in generating toxic content highlights a significant challenge in developing reliable safety guardrails for LLMs. In particular, we stress that focusing on the safety of the verbatim LLM outputs is insufficient and that we also need to consider post-hoc transformations.

Related papers

• CoCA: Regaining Safety-awareness of Multimodal Large Language Models with Constitutional Calibration [90.36429361299807]
  multimodal large language models (MLLMs) have demonstrated remarkable success in engaging in conversations involving visual inputs. The integration of visual modality has introduced a unique vulnerability: the MLLM becomes susceptible to malicious visual inputs. We introduce a technique termed CoCA, which amplifies the safety-awareness of the MLLM by calibrating its output distribution.
  arXiv  Detail & Related papers  (2024-09-17T17:14:41Z)
• Probing the Safety Response Boundary of Large Language Models via Unsafe Decoding Path Generation [44.09578786678573]
  Large Language Models (LLMs) are implicit troublemakers. LLMs could be used to gather harmful data or launch covert attacks. We name this decoding strategy: Jailbreak Value Decoding (JVD)
  arXiv  Detail & Related papers  (2024-08-20T09:11:21Z)
• ShieldGemma: Generative AI Content Moderation Based on Gemma [49.91147965876678]
  ShieldGemma is a suite of safety content moderation models built upon Gemma2. Models provide robust, state-of-the-art predictions of safety risks across key harm types.
  arXiv  Detail & Related papers  (2024-07-31T17:48:14Z)
• Robustifying Safety-Aligned Large Language Models through Clean Data Curation [11.273749179260468]
  Large language models (LLMs) are vulnerable when trained on datasets containing harmful content. In this paper, we propose a data curation framework designed to counter adversarial impacts in both scenarios.
  arXiv  Detail & Related papers  (2024-05-24T04:50:38Z)
• ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings [58.82536530615557]
  We propose an Adversarial Suffix Embedding Translation Framework (ASETF) to transform continuous adversarial suffix embeddings into coherent and understandable text. Our method significantly reduces the computation time of adversarial suffixes and achieves a much better attack success rate to existing techniques.
  arXiv  Detail & Related papers  (2024-02-25T06:46:27Z)
• MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance [36.03512474289962]
  This paper investigates the novel challenge of defending MLLMs against malicious attacks through visual inputs. Images act as a foreign language" that is not considered during safety alignment, making MLLMs more prone to producing harmful responses. We introduce MLLM-Protector, a plug-and-play strategy that solves two subtasks: 1) identifying harmful responses via a lightweight harm detector, and 2) transforming harmful responses into harmless ones via a detoxifier.
  arXiv  Detail & Related papers  (2024-01-05T17:05:42Z)
• A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly [21.536079040559517]
  Large Language Models (LLMs) have revolutionized natural language understanding and generation. This paper explores the intersection of LLMs with security and privacy.
  arXiv  Detail & Related papers  (2023-12-04T16:25:18Z)
• Multilingual Jailbreak Challenges in Large Language Models [96.74878032417054]
  In this study, we reveal the presence of multilingual jailbreak challenges within large language models (LLMs) We consider two potential risky scenarios: unintentional and intentional. We propose a novel textscSelf-Defense framework that automatically generates multilingual training data for safety fine-tuning.
  arXiv  Detail & Related papers  (2023-10-10T09:44:06Z)
• Goal-Oriented Prompt Attack and Safety Evaluation for LLMs [43.93613764464993]
  We introduce a pipeline to construct high-quality prompt attack samples, along with a Chinese prompt attack dataset called CPAD. Our prompts aim to induce LLMs to generate unexpected outputs with several carefully designed prompt attack templates. The results show that our prompts are significantly harmful to LLMs, with around 70% attack success rate to GPT-3.5.
  arXiv  Detail & Related papers  (2023-09-21T07:07:49Z)
• LLM Censorship: A Machine Learning Challenge or a Computer Security Problem? [52.71988102039535]
  We show that semantic censorship can be perceived as an undecidable problem. We argue that the challenges extend beyond semantic censorship, as knowledgeable attackers can reconstruct impermissible outputs.
  arXiv  Detail & Related papers  (2023-07-20T09:25:02Z)
• Red Teaming Language Model Detectors with Language Models [114.36392560711022]
  Large language models (LLMs) present significant safety and ethical risks if exploited by malicious users. Recent works have proposed algorithms to detect LLM-generated text and protect LLMs. We study two types of attack strategies: 1) replacing certain words in an LLM's output with their synonyms given the context; 2) automatically searching for an instructional prompt to alter the writing style of the generation.
  arXiv  Detail & Related papers  (2023-05-31T10:08:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.