English
Related papers

Related papers: Sparse Tokens Suffice: Jailbreaking Audio Language…

200 papers

The Segment Anything Model (SAM) achieves strong open-vocabulary segmentation, but its ViT-based image encoders dominate inference latency and memory. Existing activation compression methods, such as token merging, reduce the token length…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Hoai-Chau Tran , Chi H. Nguyen , Duy M. H. Nguyen , Mathias Niepert , Fan Lai , Khoa D. Doan

Identifying the vulnerabilities of large language models (LLMs) is crucial for improving their safety by addressing inherent weaknesses. Jailbreaks, in which adversaries bypass safeguards with crafted input prompts, play a central role in…

Artificial Intelligence · Computer Science 2026-04-03 Hamin Koo , Minseon Kim , Jaehyung Kim

Large Language Models (LLMs) are increasingly exposed to adaptive jailbreaking, particularly in high-stakes Chemical, Biological, Radiological, and Nuclear (CBRN) domains. Although streaming probes enable real-time monitoring, they still…

Computation and Language · Computer Science 2026-04-17 Xuanli He , Bilgehan Sel , Faizan Ali , Jenny Bao , Hoagy Cunningham , Jerry Wei

Large Language Models (LLMs) excel at various natural language processing tasks but remain vulnerable to jailbreaking attacks that induce harmful content generation. In this paper, we reveal a critical safety inconsistency: LLMs can more…

Computation and Language · Computer Science 2025-08-27 Peng Ding , Wen Sun , Dailin Li , Wei Zou , Jiaming Wang , Jiajun Chen , Shujian Huang

While multi-audio understanding is critical for large audio-language models (LALMs), it remains underexplored. We introduce MUGEN, a comprehensive benchmark evaluating this capability across speech, general audio, and music. Our experiments…

The safety alignment of current Large Language Models (LLMs) is vulnerable. Relatively simple attacks, or even benign fine-tuning, can jailbreak aligned models. We argue that many of these vulnerabilities are related to a shared underlying…

Cryptography and Security · Computer Science 2024-06-11 Xiangyu Qi , Ashwinee Panda , Kaifeng Lyu , Xiao Ma , Subhrajit Roy , Ahmad Beirami , Prateek Mittal , Peter Henderson

Integrating audio comprehension and generation into large language models (LLMs) remains challenging due to the continuous nature of audio and the resulting high sampling rates. Here, we introduce a novel approach that combines Variational…

Audio and Speech Processing · Electrical Eng. & Systems 2025-03-31 Shivam Mehta , Nebojsa Jojic , Hannes Gamper

Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks. Direct preference optimization (DPO), a widely deployed alignment method, exhibits limitations in both experimental…

Computation and Language · Computer Science 2025-10-31 Xuandong Zhao , Will Cai , Tianneng Shi , David Huang , Licong Lin , Song Mei , Dawn Song

Large Language Models (LLMs) demonstrate impressive zero-shot performance across a wide range of natural language processing tasks. Integrating various modality encoders further expands their capabilities, giving rise to Multimodal Large…

Sound · Computer Science 2026-01-13 Hao Cheng , Erjia Xiao , Jing Shao , Yichi Wang , Le Yang , Chao Shen , Philip Torr , Jindong Gu , Renjing Xu

Fine-tuning large language models (LLMs) for downstream tasks has become increasingly crucial due to their widespread use and the growing availability of open-source models. However, the high memory costs associated with fine-tuning remain…

Machine Learning · Computer Science 2025-02-04 David H. Yang , Mohammad Mohammadi Amiri , Tejaswini Pedapati , Subhajit Chaudhury , Pin-Yu Chen

We propose a communication-efficient optimally structured gradient coding scheme to jointly address straggler resilience and communication efficiency in heterogeneous distributed learning. By establishing a unified framework that…

Systems and Control · Electrical Eng. & Systems 2026-05-18 Heekang Song , Wan Choi

Machine unlearning has emerged as a critical capability for addressing privacy, safety, and regulatory concerns in large language models (LLMs). Existing methods operate at the sequence level, applying uniform updates across all tokens…

Computation and Language · Computer Science 2026-05-07 Jiawei Wu , Doudou Zhou

Recent advances in end-to-end trained omni-models have significantly improved multimodal understanding. At the same time, safety red-teaming has expanded beyond text to encompass audio-based jailbreak attacks. However, an important bridge…

Machine Learning · Computer Science 2026-02-04 Yupeng Chen , Junchi Yu , Aoxi Liu , Philip Torr , Adel Bibi

Large language models (LLMs) are now ubiquitous in user-facing applications, yet they still generate undesirable toxic outputs, including profanity, vulgarity, and derogatory remarks. Although numerous detoxification methods exist, most…

Computation and Language · Computer Science 2025-10-24 Agam Goyal , Vedant Rathi , William Yeh , Yian Wang , Yuen Chen , Hari Sundaram

Recent success of deep neural networks (DNNs) hinges on the availability of large-scale dataset; however, training on such dataset often poses privacy risks for sensitive training information. In this paper, we aim to explore the power of…

Machine Learning · Computer Science 2022-03-29 Boxin Wang , Fan Wu , Yunhui Long , Luka Rimanic , Ce Zhang , Bo Li

While language models (LMs) paired with residual vector quantization (RVQ) tokenizers have shown promise in text-to-audio (T2A) generation, they still lag behind diffusion-based models by a non-trivial margin. We identify a critical dilemma…

Sound · Computer Science 2025-10-07 Juncheng Wang , Chao Xu , Cheng Yu , Zhe Hu , Haoyu Xie , Guoqi Yu , Lei Shang , Shujun Wang

Despite the strong performance of large audio language models (LALMs) in various tasks, exactly how and where they integrate acoustic features with textual context remains unclear. We adapt causal tracing to investigate the internal…

Sound · Computer Science 2026-03-17 Wei-Chih Chen , Chien-yu Huang , Hung-yi Lee

Despite advances in AI alignment, large language models (LLMs) remain vulnerable to adversarial attacks or jailbreaking, in which adversaries can modify prompts to induce unwanted behavior. While some defenses have been proposed, they have…

Machine Learning · Computer Science 2024-11-11 Andy Zhou , Bo Li , Haohan Wang

Large Language Models have shown impressive generative capabilities across diverse tasks, but their safety remains a critical concern. Existing post-training alignment methods, such as SFT and RLHF, reduce harmful outputs yet leave LLMs…

Cryptography and Security · Computer Science 2025-10-21 Zhengyue Zhao , Yingzi Ma , Somesh Jha , Marco Pavone , Patrick McDaniel , Chaowei Xiao

Audio temporal forgery localization (ATFL) aims to find the precise forgery regions of the partial spoof audio that is purposefully modified. Existing ATFL methods rely on training efficient networks using fine-grained annotations, which…

Sound · Computer Science 2025-05-08 Junyan Wu , Wenbo Xu , Wei Lu , Xiangyang Luo , Rui Yang , Shize Guo