{"list":"other","total":64,"rows":[{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2311.07919","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","created":"2023-11-14","cited_by_count":608},{"id":"1801.01944","title":"Audio Adversarial Examples: Targeted Attacks on Speech-to-Text","created":"2018-01-05","cited_by_count":274},{"id":"2409.06666","title":"LLaMA-Omni: Seamless Speech Interaction with Large Language Models","created":"2024-09-10","cited_by_count":173},{"id":"2402.13457","title":"A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models","created":"2024-02-21","cited_by_count":106},{"id":"2402.05668","title":"JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs","created":"2024-02-08","cited_by_count":95},{"id":"2305.01219","title":"Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models","created":"2023-05-02","cited_by_count":94},{"id":"2412.03556","title":"Best-of-N Jailbreaking","created":"2024-12-04","cited_by_count":76},{"id":"2407.05965","title":"T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models","created":"2024-07-08","cited_by_count":66},{"id":"2401.05949","title":"Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning","created":"2024-01-11","cited_by_count":53},{"id":"2403.01255","title":"Automatic Speech Recognition using Advanced Deep Learning Approaches: A survey","created":"2024-03-02","cited_by_count":50},{"id":"2107.14569","title":"Can You Hear It? Backdoor Attacks via Ultrasonic Triggers","created":"2021-07-30","cited_by_count":44},{"id":"2405.19103","title":"Voice Jailbreak Attacks Against GPT-4o","created":"2024-05-29","cited_by_count":42},{"id":"1805.07820","title":"Targeted Adversarial Examples for Black Box Audio Systems","created":"2018-05-20","cited_by_count":41},{"id":"2103.03344","title":"WaveGuard: Understanding and Mitigating Audio Adversarial Examples","created":"2021-03-04","cited_by_count":40},{"id":"2406.06302","title":"Unveiling the Safety of GPT-4o: An Empirical Study using Jailbreak Attacks","created":"2024-06-10","cited_by_count":38},{"id":"2412.08608","title":"AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models","created":"2024-12-11","cited_by_count":38},{"id":"2004.12261","title":"Enabling Fast and Universal Audio Adversarial Attack Using Generative Model","created":"2020-04-26","cited_by_count":32},{"id":"2411.09259","title":"Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey","created":"2024-11-14","cited_by_count":32},{"id":"2410.14425","title":"Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation","created":"2024-10-18","cited_by_count":27},{"id":"2110.09714","title":"Black-box Adversarial Attacks on Commercial Speech Platforms with Minimal Information","created":"2021-10-19","cited_by_count":25},{"id":"2206.03393","title":"Towards Understanding and Mitigating Audio Adversarial Examples for Speaker Recognition","created":"2022-06-07","cited_by_count":23},{"id":"2303.01507","title":"Defending against Adversarial Audio via Diffusion Model","created":"2023-03-02","cited_by_count":23},{"id":"2211.03117","title":"Going In Style: Audio Backdoors Through Stylistic Transformations","created":"2022-11-06","cited_by_count":21},{"id":"2409.09272","title":"SafeEar: Content Privacy-Preserving Audio Deepfake Detection","created":"2024-09-14","cited_by_count":21},{"id":"1911.00126","title":"Adversarial Music: Real World Audio Adversary Against Wake-word Detection System","created":"2019-10-31","cited_by_count":20},{"id":"2505.11217","title":"Seeing Sound, Hearing Sight: Uncovering Modality Bias and Conflict of AI models in Sound Localization","created":"2025-05-16","cited_by_count":18},{"id":"2402.12168","title":"Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning","created":"2024-02-19","cited_by_count":16},{"id":"2312.14398","title":"ZMM-TTS: Zero-shot Multilingual and Multispeaker Speech Synthesis Conditioned on Self-supervised Discrete Speech Representations","created":"2023-12-22","cited_by_count":15},{"id":"2403.13507","title":"FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMs","created":"2024-03-20","cited_by_count":14},{"id":"2409.14743","title":"LlamaPartialSpoof: An LLM-Driven Fake Speech Dataset Simulating Disinformation Generation","created":"2024-09-23","cited_by_count":14},{"id":"2502.05863","title":"Uni-Retrieval: A Multi-Style Retrieval Framework for STEM's Education","created":"2025-02-09","cited_by_count":13},{"id":"1904.10990","title":"A Robust Approach for Securing Audio Classification Against Adversarial Attacks","created":"2019-04-24","cited_by_count":12},{"id":"2409.06793","title":"Adversarial Attacks to Multi-Modal Models","created":"2024-09-10","cited_by_count":12},{"id":"2408.01867","title":"TrustNavGPT: Modeling Uncertainty to Improve Trustworthiness of Audio-Guided LLM-Based Robot Navigation","created":"2024-08-03","cited_by_count":11},{"id":"2312.09665","title":"FlowMur: A Stealthy and Practical Audio Backdoor Attack with Limited Knowledge","created":"2023-12-15","cited_by_count":10},{"id":"2406.19311","title":"Zero-Query Adversarial Attack on Black-box Automatic Speech Recognition Systems","created":"2024-06-27","cited_by_count":10},{"id":"2501.11902","title":"Transferable Adversarial Attacks on Audio Deepfake Detection","created":"2025-01-21","cited_by_count":9},{"id":"1912.08639","title":"Detecting Adversarial Attacks On Audiovisual Speech Recognition","created":"2019-12-18","cited_by_count":8},{"id":"2309.06981","title":"MASTERKEY: Practical Backdoor Attack Against Speaker Verification Systems","created":"2023-09-13","cited_by_count":8},{"id":"2502.00718","title":"\"I am bad\": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models","created":"2025-02-02","cited_by_count":8},{"id":"1904.03829","title":"Adversarial Audio: A New Information Hiding Method and Backdoor for DNN-based Speech Recognition Models","created":"2019-04-08","cited_by_count":7},{"id":"2301.00986","title":"Look, Listen, and Attack: Backdoor Attacks Against Video Action Recognition","created":"2023-01-03","cited_by_count":7},{"id":"2303.15940","title":"TransAudio: Towards the Transferable Adversarial Audio Attack via Learning Contextualized Perturbations","created":"2023-03-28","cited_by_count":7},{"id":"2502.00735","title":"`From Prompt to Perturbation': An Adaptive Framework for Voice-Based Jailbreaks on Audio LLMs","created":"2025-02-02","cited_by_count":7},{"id":"2505.17050","title":"Towards Robust Evaluation of STEM Education: Leveraging MLLMs in Project-Based Learning","created":"2025-05-16","cited_by_count":7},{"id":"2205.13685","title":"Adversarial attacks and defenses in Speaker Recognition Systems: A survey","created":"2022-05-27","cited_by_count":6},{"id":"2307.13643","title":"Backdoor Attacks against Voice Recognition Systems: A Survey","created":"2023-07-23","cited_by_count":6},{"id":"2409.06372","title":"SpeechTaxi: On Multilingual Semantic Speech Classification","created":"2024-09-10","cited_by_count":6},{"id":"2010.03164","title":"Adversarial attacks on audio source separation","created":"2020-10-07","cited_by_count":5},{"id":"2306.16022","title":"Enrollment-stage Backdoor Attacks on Speaker Recognition Systems via Adversarial Ultrasound","created":"2023-06-28","cited_by_count":5},{"id":"2309.06960","title":"PhantomSound: Black-Box, Query-Efficient Audio Adversarial Attack via Split-Second Phoneme Injection","created":"2023-09-13","cited_by_count":5},{"id":"2406.10932","title":"Imperceptible Rhythm Backdoor Attacks: Exploring Rhythm Transformation for Embedding Undetectable Vulnerabilities on Speech Recognition","created":"2024-06-16","cited_by_count":5},{"id":"2408.01178","title":"EmoBack: Backdoor Attacks Against Speaker Identification Using Emotional Prosody","created":"2024-08-02","cited_by_count":5},{"id":"2408.01808","title":"ALIF: Low-Cost Adversarial Audio Attacks on Black-Box Speech Platforms using Linguistic Features","created":"2024-08-03","cited_by_count":5},{"id":"2404.00076","title":"A Backdoor Approach with Inverted Labels Using Dirty Label-Flipping Attacks","created":"2024-03-29","cited_by_count":4},{"id":"2308.04179","title":"Breaking Speaker Recognition with PaddingBack","created":"2023-08-08","cited_by_count":3},{"id":"2401.01537","title":"The Art of Deception: Robust Backdoor Attack using Dynamic Stacking of Triggers","created":"2024-01-03","cited_by_count":3},{"id":"2406.10719","title":"Trading Devil: Robust backdoor attack via Stochastic investment models and Bayesian approach","created":"2024-06-15","cited_by_count":3},{"id":"2211.10661","title":"Phonemic Adversarial Attack against Audio Recognition in Real World","created":"2022-11-19","cited_by_count":2},{"id":"2304.10088","title":"Towards the Universal Defense for Query-Based Audio Adversarial Attacks","created":"2023-04-20","cited_by_count":2},{"id":"2408.15508","title":"EmoAttack: Utilizing Emotional Voice Conversion for Speech Backdoor Attacks on Deep Speech Classification Models","created":"2024-08-28","cited_by_count":2},{"id":"2502.11858","title":"Rethinking Audio-Visual Adversarial Vulnerability from Temporal and Modality Perspectives","created":"2025-02-17","cited_by_count":2},{"id":"2408.13849","title":"Sample-Independent Federated Learning Backdoor Attack in Speaker Recognition","created":"2024-08-25","cited_by_count":1}],"next_cursor":null}