{"total":16,"rows":[{"id":"2406.14796","title":"MU-Bench: A Multitask Multimodal Benchmark for Machine Unlearning","created":"2024-06-21","cited_by_count":17,"area":"safety"},{"id":"2111.05113","title":"Membership Inference Attacks Against Self-supervised Speech Models","created":"2021-11-09","cited_by_count":16,"area":"safety"},{"id":"2412.16633","title":"Easier Said Than Done: Unpacking Intent-Behavior Gap in Jailbreaking LLM-Based Robots","created":"2024-12-21","cited_by_count":15,"area":"safety"},{"id":"2506.00848","title":"Speech Unlearning","created":"2025-06-01","cited_by_count":7,"area":"safety"},{"id":"2403.03846","title":"Can Distillation Mitigate Backdoor Attacks in Pre-trained Encoders?","created":"2024-03-06","cited_by_count":6,"area":"safety"},{"id":"2507.20140","title":"Do Not Mimic My Voice: Speaker Identity Unlearning for Zero-Shot Text-to-Speech","created":"2025-07-27","cited_by_count":6,"area":"safety"},{"id":"2505.15700","title":"\"Alexa, can you forget me?\" Machine Unlearning Benchmark in Spoken Language Understanding","created":"2025-05-21","cited_by_count":5,"area":"safety"},{"id":"2508.03365","title":"When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs","created":"2025-08-05","cited_by_count":4,"area":"safety"},{"id":"2403.05842","title":"TokenMark: A Modality-Agnostic Watermark for Pre-trained Transformers","created":"2024-03-09","cited_by_count":1,"area":"safety"},{"id":"2510.01157","title":"Where Do Backdoors Live? A Component-Level Analysis of Backdoor Propagation in Speech Language Models","created":"2025-10-01","cited_by_count":1,"area":"safety"},{"id":"2605.25962","title":"Continual Speaker Identity Unlearning with Minimal Interference","created":"2026-05-25","cited_by_count":1,"area":"safety"},{"id":"2606.06837","title":"SEAM: Shortcut-Aware Real-Time Detection of Scripted vs. Spontaneous Speech for Interview Guardrails","created":"2026-06-05","cited_by_count":1,"area":"safety"},{"id":"2403.16151","title":"Ultra Low-Cost Two-Stage Multimodal System for Non-Normative Behavior Detection","created":"2024-03-24","cited_by_count":0,"area":"safety"},{"id":"2602.10166","title":"MerkleSpeech: Public-Key Verifiable, Chunk-Localised Speech Provenance via Perceptual Fingerprints and Merkle Commitments","created":"2026-02-10","cited_by_count":0,"area":"safety"},{"id":"2604.13127","title":"Graph Propagated Projection Unlearning: A Unified Framework for Vision and Audio Discriminative Models","created":"2026-04-13","cited_by_count":0,"area":"safety"},{"id":"2606.21052","title":"Backdoor Attacks on Speech Emotion Recognition via TTS-Generated Poisoning","created":"2026-06-19","cited_by_count":0,"area":"safety"}],"next_cursor":null}