ARENA: Automated Red-Teaming for Large Audio Language Models

• URL: http://arxiv.org/abs/2608.15578v1
• Date: Sun, 16 Aug 2026 07:03:53 GMT
• Title: ARENA: Automated Red-Teaming for Large Audio Language Models
• Abstract summary: We study automated audio-grounded red-teaming, where a text query must remain safe in isolation while the joint text-audio input induces harmful target behavior.<n>We propose ARENA, a closed-loop framework that trains a controller on an independent 2,000case text-audio dataset.<n>On 520 held-out AdvBench objectives, ARENA achieves FDR/PSR of 87.9/100.0%, 71.5/96.3%, 68.1/100.0%, and 75.4/98.5%.
• Score: 30.804646851033567
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large audio-language models (LALMs) make it possible to interact with language models through speech, music, and environmental sound, but they also introduce a safety surface that is difficult to expose with text-only red-teaming. We study automated audio-grounded red-teaming, where a text query must remain safe in isolation while the joint text-audio input induces harmful target behavior. We propose ARENA, a closed-loop framework that trains a controller on an independent 2,000case text-audio dataset. MD-Judge supplies training rewards and adaptive search feedback, while a separate, non-adaptive Llama Guard 3 evaluator alone labels final outcomes. On 520 held-out AdvBench objectives, ARENA achieves FDR/PSR of 87.9/100.0%, 71.5/96.3%, 68.1/100.0%, and 75.4/98.5% on Audio Flamingo 3, Qwen2-Audio, MiMo-Audio, and GPTAudio, respectively. Ablations show that feedback-based refinement and audio-variant search substantially improve attack discovery.

Related papers

• Unified Audio Intelligence Without Regressing on Text Intelligence [86.55418188552768]
  We introduce Nemotron-Labs-Audex-30B-A3B (Audex), a unified audio-text LLM.<n>Audex adopts a simple unified design with a single Transformer decoder.<n>Audex delivers state-of-the-art audio understanding, speech recognition and translation, text-to-speech, audio generation, and speech-to-speech generation.
  arXiv  Detail & Related papers  (2026-07-06T15:11:57Z)
• 2nd of the 5th PVUW MeViS-Audio Track: ASR-SaSaSa2VA [47.992210130090065]
  We present ASR-SaSa2VA, a resource-efficient framework for audio-guided video segmentation.<n>Our approach achieves a final score of 80.7 in the 5th PVUW Challenge (MeViS-v2-Audio track), earning the second-place ranking.
  arXiv  Detail & Related papers  (2026-04-27T01:19:56Z)
• VoiceSHIELD-Small: Real-Time Malicious Speech Detection and Transcription [2.0225826789157404]
  This paper introduces VoiceSHIELD-Small, a lightweight model that works in real time.<n>It can transcribe speech and detect whether it is safe or harmful, all in one step.<n>Built on OpenAI's Whisper-small encoder, VoiceSHIELD adds a mean-pooling layer and a simple classification head.
  arXiv  Detail & Related papers  (2026-03-08T16:23:42Z)
• SAM Audio Judge: A Unified Multimodal Framework for Perceptual Evaluation of Audio Separation [52.468945848774844]
  This paper addresses the need for automated systems capable of evaluating audio separation without human intervention.<n>The proposed evaluation metric, SAM Audio Judge (SAJ), is a multimodal fine-grained reference-free objective metric.<n>SAJ supports three audio domains (speech, music and general sound events) and three prompt inputs (text, visual and span), covering four different dimensions of evaluation.
  arXiv  Detail & Related papers  (2026-01-27T15:29:02Z)
• Adaptive vector steering: A training-free, layer-wise intervention for hallucination mitigation in large audio and multimodal models [45.88028371034407]
  We propose Adaptive Vector Steering to better grounds generation in audio content.<n>Experiments show consistent performance gains across two models and two benchmarks.<n>To the best of our knowledge, this is the first work to apply vector steering to mitigate hallucination in audio.
  arXiv  Detail & Related papers  (2025-10-14T08:52:18Z)
• MDAR: A Multi-scene Dynamic Audio Reasoning Benchmark [64.89810922949984]
  We introduce MDAR, a benchmark for evaluating models on complex, multi-scene, and dynamically evolving audio reasoning tasks.<n>MDAR comprises 3,000 carefully curated question-answer pairs linked to diverse audio clips.<n>We benchmark 26 state-of-the-art audio language models on MDAR and observe that they exhibit limitations in complex reasoning tasks.
  arXiv  Detail & Related papers  (2025-09-26T15:12:46Z)
• AHELM: A Holistic Evaluation of Audio-Language Models [78.20477815156484]
  multimodal audio-language models (ALMs) take interleaved audio and text as input and output text.<n>AHELM is a benchmark that aggregates various datasets -- including 2 new synthetic audio-text datasets called PARADE and CoRe-Bench.<n>We also standardize the prompts, inference parameters, and evaluation metrics to ensure equitable comparisons across models.
  arXiv  Detail & Related papers  (2025-08-29T07:40:39Z)
• Audio Does Matter: Importance-Aware Multi-Granularity Fusion for Video Moment Retrieval [58.640807985155554]
  Video Moment Retrieval (VMR) aims to retrieve a specific moment semantically related to a given query.<n>Most existing VMR methods solely focus on the visual and textual modalities while neglecting the complementary but important audio modality.<n>We propose a novel Importance-aware Multi-Granularity fusion model (IMG), which learns to dynamically and selectively aggregate the audio-vision-text contexts for VMR.
  arXiv  Detail & Related papers  (2025-08-06T09:58:43Z)
• Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal Models [50.89022445197919]
  We show that open-source audio LMMs suffer an average attack success rate of 69.14% on harmful audio questions. Our speech-specific jailbreaks on Gemini-1.5-Pro achieve an attack success rate of 70.67% on the harmful query benchmark.
  arXiv  Detail & Related papers  (2024-10-31T12:11:17Z)
• Automated Audio Captioning and Language-Based Audio Retrieval [3.9065205774219334]
  This project involved two subtasks: Automated Audio Captioning and Language-Based Audio Retrieval. For both subtasks, the Clotho dataset was used. Models were evaluated on BLEU1, BLEU2, BLEU3, ROUGEL, METEOR, CIDEr, SPICE, and SPIDEr scores for audio captioning and R1, R5, R10 and mARP10 scores for audio retrieval.
  arXiv  Detail & Related papers  (2022-07-08T23:48:52Z)
• Robust Self-Supervised Audio-Visual Speech Recognition [29.526786921769613]
  We present a self-supervised audio-visual speech recognition framework built upon Audio-Visual HuBERT (AV-HuBERT) On the largest available AVSR benchmark dataset LRS3, our approach outperforms prior state-of-the-art by 50% (28.0% vs. 14.1%) using less than 10% of labeled data. Our approach reduces the WER of an audio-based model by over 75% (25.8% vs. 5.8%) on average.
  arXiv  Detail & Related papers  (2022-01-05T18:50:50Z)

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.