arXiv AI
Jun 17
Membership Inference Attacks against Large Audio Language Models
arXiv:2603. 28378v2 Announce Type: replace-cross Abstract: We present the first systematic Membership Inference Attack (MIA) evaluation of LALMs.
Amplifying Membership Signal Through Chained Regeneration
arXiv:2606. 31991v1 Announce Type: cross Abstract: The tendency of large generative models to memorize training data makes sample verification critical for privacy auditing and copyright enforcement.
Related stories
arXiv AI
Jun 24
MGI: Member vs Generated Inference
arXiv:2606. 23872v1 Announce Type: cross Abstract: As generative models increasingly produce samples that are indistinguishable from human-created content, it becomes difficult to determine whether a given data point was part of a model's natural training set or was generated by the model itself, especially when models memorize and reproduce training data.
arXiv Machine Learning
Aug 14
Noise as a Probe: Membership Inference Attacks on Diffusion Models Leveraging Initial Noise
arXiv:2601. 21628v2 Announce Type: replace-cross Abstract: Diffusion models have achieved remarkable progress in image generation, but their increasing deployment raises serious concerns about privacy and copyright.
arXiv AI
Aug 12
Where Flow Matching Leaks: Characterising Membership Signals Along the Interpolation Path
arXiv:2606. 07271v3 Announce Type: replace-cross Abstract: Understanding memorization in generative models remains challenging, with implications for copyright and privacy.
arXiv Machine Learning
Jul 15
Generalization and Memorization in Rectified Flow
arXiv:2603. 13421v2 Announce Type: replace Abstract: Generative models based on the Flow Matching objective, particularly Rectified Flow, have emerged as a dominant paradigm for efficient, high-fidelity image synthesis.
arXiv Machine Learning
1d ago
AnchorPrompt: Self-Distilled Soft Prompts for Robust Audio-Language Models
AnchorPrompt is an adaptation technique for large audio‑language models that keeps the base model frozen and learns a single block of prompt vectors inserted at the decoder input. By training these prompts through self‑distillation on diverse audio and text perturbations, the method improves answer consistency and reduces hallucinations across multiple benchmarks. The approach is perturbation‑agnostic at inference, enabling zero‑shot transfer to unseen distortions such as reverberation and choice permutations.
arXiv AI
Jun 8
Where Rectified Flows Leak: Characterising Membership Signals Along the Interpolation Path
arXiv:2606. 07271v1 Announce Type: cross Abstract: Understanding what generative models retain from training data remains challenging, with implications for copyright and privacy.
arXiv Machine Learning
Sep 3
Hearing the Whispers: Black-Box Membership Inference Attacks on Finetuned TTS Models
The paper introduces a black-box membership inference attack framework tailored for fine-tuned text-to-speech models, addressing challenges in query generation and representation engineering. It evaluates five query types, finding recitation queries most effective, and uses multi-level speech embeddings with temporal alignment for fine-grained comparison. Experiments on CosyVoice2, F5-TTS, and XTTS-v2 trained on VCTK and British Dialect datasets show high privacy leakage, with speaker-level AUC above 0.80 and record-level AUC between 0.80 and 0.90.
arXiv AI
Jul 7
One Framework for All: Cross-Modal Membership Inference for Generative Models
arXiv:2607. 04339v1 Announce Type: cross Abstract: Large generative models across text-to-text, text-to-image, and image-to-text modalities have been shown to pose significant privacy risks.
arXiv Machine Learning
Jul 24
Enhancing Membership Inference Attacks on Diffusion Models from a Frequency-Domain Perspective
arXiv:2505. 20955v5 Announce Type: replace-cross Abstract: Diffusion models have achieved tremendous success in image generation, but they also raise significant concerns regarding privacy and copyright issues.
arXiv Machine Learning
Sep 18
Automated Membership Inference Attacks (AutoMIA): Discovering MIA Signal Computations using LLM Agents
The paper introduces AutoMIA, a framework that uses large language model agents to automatically design and implement new membership inference attack (MIA) signal computations. By systematically exploring a wide range of attack strategies, AutoMIA discovers novel MIAs tailored to specific target models and datasets, achieving up to a 0.18 absolute improvement in AUC over existing methods. This demonstrates that LLM agents can serve as an effective and scalable approach for creating state‑of‑the‑art MIAs.
arXiv AI
2d ago
External Observers May See More Clearly: Cross-Model Span-Level Hallucination Detection in Large Language Models via Hidden State Probing
The paper proposes a hidden‑state probing method for detecting hallucinations at the span level in large language model outputs, moving beyond token‑wise binary classification. By examining layer‑wise activation patterns, the approach identifies the exact onset and continuation tokens of hallucinations, achieving higher precision‑recall AUC than random baselines despite class imbalance. Additionally, the authors introduce a cross‑model detection framework where one model observes another’s internal representations, showing that an external observer can match or surpass the generator’s own self‑detection of hallucination onsets, even when the observer is smaller.