Who Can Withstand Chat-Audio Attacks? An Evaluation Benchmark for Large Language Models

• URL: http://arxiv.org/abs/2411.14842v1
• Date: Fri, 22 Nov 2024 10:30:48 GMT
• Title: Who Can Withstand Chat-Audio Attacks? An Evaluation Benchmark for Large Language Models
• Authors: Wanqi Yang, Yanda Li, Meng Fang, Yunchao Wei, Tianyi Zhou, Ling Chen,
• Abstract summary: Adrial audio attacks pose a significant threat to the growing use of large language models (LLMs) in voice-based human-machine interactions. We introduce the Chat-Audio Attacks benchmark including four distinct types of audio attacks. We evaluate six state-of-the-art LLMs with voice interaction capabilities, including Gemini-1.5-Pro, GPT-4o, and others.
• Score: 70.99768410765502
• License:
• Abstract: Adversarial audio attacks pose a significant threat to the growing use of large language models (LLMs) in voice-based human-machine interactions. While existing research has primarily focused on model-specific adversarial methods, real-world applications demand a more generalizable and universal approach to audio adversarial attacks. In this paper, we introduce the Chat-Audio Attacks (CAA) benchmark including four distinct types of audio attacks, which aims to explore the the vulnerabilities of LLMs to these audio attacks in conversational scenarios. To evaluate the robustness of LLMs, we propose three evaluation strategies: Standard Evaluation, utilizing traditional metrics to quantify model performance under attacks; GPT-4o-Based Evaluation, which simulates real-world conversational complexities; and Human Evaluation, offering insights into user perception and trust. We evaluate six state-of-the-art LLMs with voice interaction capabilities, including Gemini-1.5-Pro, GPT-4o, and others, using three distinct evaluation methods on the CAA benchmark. Our comprehensive analysis reveals the impact of four types of audio attacks on the performance of these models, demonstrating that GPT-4o exhibits the highest level of resilience.

Related papers

• A Suite for Acoustic Language Model Evaluation [20.802090523583196]
  We introduce SALMon, a novel evaluation suite encompassing background noise, emotion, speaker identity and room impulse response. We evaluate several speech language models on SALMon, thus highlighting the strengths and weaknesses of each evaluated method.
  arXiv  Detail & Related papers  (2024-09-11T17:34:52Z)
• Enhancing Audio-Language Models through Self-Supervised Post-Training with Text-Audio Pairs [3.8300818830608345]
  Multi-modal contrastive learning strategies for audio and text have rapidly gained interest. The ability of these models to understand natural language and temporal relations is still a largely unexplored and open field for research. We propose to equip the multi-modal ALMs with temporal understanding without loosing their inherent prior capabilities of audio-language tasks with a temporal instillation method TeminAL.
  arXiv  Detail & Related papers  (2024-08-17T18:53:17Z)
• KGPA: Robustness Evaluation for Large Language Models via Cross-Domain Knowledge Graphs [5.798411590796167]
  This paper proposes a framework that systematically evaluates the robustness of large language models under adversarial attack scenarios. Our framework generates original prompts from the triplets of knowledge graphs and creates adversarial prompts by poisoning. Experiments show that adversarial robustness of the ChatGPT family ranks as GPT-4-turbo > GPT-4o > GPT-3.5-turbo, and the robustness of large language models is influenced by the professional domains in which they operate.
  arXiv  Detail & Related papers  (2024-06-16T04:48:43Z)
• AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension [95.8442896569132]
  We introduce AIR-Bench, the first benchmark to evaluate the ability of Large Audio-Language Models (LALMs) to understand various types of audio signals and interact with humans in the textual format. Results demonstrate a high level of consistency between GPT-4-based evaluation and human evaluation.
  arXiv  Detail & Related papers  (2024-02-12T15:41:22Z)
• AV-SUPERB: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models [92.92233932921741]
  We propose the AV-SUPERB benchmark that enables general-purpose evaluation of unimodal audio/visual and bimodal fusion representations. We evaluate 5 recent self-supervised models and show that none of these models generalize to all tasks. We show that representations may be improved with intermediate-task fine-tuning and audio event classification with AudioSet serves as a strong intermediate task.
  arXiv  Detail & Related papers  (2023-09-19T17:35:16Z)
• Membership Inference Attacks Against Self-supervised Speech Models [62.73937175625953]
  Self-supervised learning (SSL) on continuous speech has started gaining attention. We present the first privacy analysis on several SSL speech models using Membership Inference Attacks (MIA) under black-box access.
  arXiv  Detail & Related papers  (2021-11-09T13:00:24Z)
• Scenario Aware Speech Recognition: Advancements for Apollo Fearless Steps & CHiME-4 Corpora [70.46867541361982]
  We consider a general non-semantic speech representation, which is trained with a self-supervised criteria based on triplet loss called TRILL. We observe +5.42% and +3.18% relative WER improvement for the development and evaluation sets of Fearless Steps.
  arXiv  Detail & Related papers  (2021-09-23T00:43:32Z)
• ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models [64.03398193325572]
  Inference attacks against Machine Learning (ML) models allow adversaries to learn about training data, model parameters, etc. We concentrate on four attacks - namely, membership inference, model inversion, attribute inference, and model stealing. Our analysis relies on a modular re-usable software, ML-Doctor, which enables ML model owners to assess the risks of deploying their models.
  arXiv  Detail & Related papers  (2021-02-04T11:35:13Z)

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.