arXiv Machine Learning October 23, 2026 By Qi Li, Xinchao Wang

OP-Print: Tracing Membership Imprints in On-Policy Self-Distillation

Read the original on arXiv Machine Learning →

The paper introduces OP-Print, a unified framework for membership inference attacks on on‑policy self‑distillation models. It shows that the supervision signal in such distillation is sparse and structured, focusing on uncertainty‑sensitive correction sites, and exploits this property to construct attack signals for both gray‑box and black‑box threat models. Experiments demonstrate that OP‑Print outperforms baseline attacks, which remain near random guessing, across various models and distillation schemes.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 14

What Does It Mean to Break a Distillation Defense?

arXiv:2606. 25059v2 Announce Type: replace-cross Abstract: Black-box LLMs (accessible only via API) are vulnerable to distillation attacks, in which an attacker queries the model and trains a student on its outputs.

By Lena Libon, Pura Peetathawatchai, Michael Aerni, Daniel Paleka, Florian Tram\`er

llms efficiency

arXiv AI

Oct 7

Does On-Policy Distillation for Safety Pose Backdoor Risks?

arXiv:2610.07654v1 Announce Type: cross Abstract: On-policy distillation (OPD) has attracted growing attention as an effective way to transfer capabilities from teacher models to student models. Rece...

By Jian Luo, Kehan Qi, Qingqiao Hu, Meilong Xu, Jiacheng Qiu, Weimin Lyu, Jiawei Zhou, Chao Chen

llms efficiency multimodal safety

arXiv Machine Learning

Oct 8

RAISED: Self-Distillation for Robustness to Prompt Injection in LLM Agents

arXiv:2610.06401v2 Announce Type: replace-cross Abstract: Tool-using language-model agents are vulnerable to indirect prompt injection because they must act on untrusted external content. Existing tr...

By Mohamed Dhouib, Clement Elliker, Alexi Canesse, Ma\"el Jenny, Lucas-Andrei Thil, Mahammed El Sharkawy, Sonia Vanier, Elie Bursztein

llms agents efficiency benchmarks

arXiv AI

Sep 30

OPFL: Optimistic Verification of Federated Learning via Empirical Boundary

arXiv:2609.37011v1 Announce Type: cross Abstract: Federated learning enables multiple clients to collaboratively train models without sharing their private data. However, the lack of visibility into...

By Hongxu Su, Jianzhu Yao, Xuechao Wang, Pramod Viswanath

robotics multimodal safety

Hugging Face Trending Papers

Jul 30

TriShield: Zero-Utility-Loss Defense Against Privacy Backdoors in Federated Language Model Fine-Tuning via Orthogonal Gradient Projection and Optimizer State Entanglement

Federated fine-tuning of large language models (LLMs) enables collaborative training without exposing raw data. However, a recent attack, NeuroImprint [1] (arXiv:2606.

llms fine-tuning safety

arXiv AI

Jun 15

From Prompts to Responses: Dual-Sided Data Leakage and Defense in Split Large Language Models

arXiv:2606. 14210v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in privacy-sensitive domains, where users must balance the risk of data exposure through external APIs against the high computational cost of local deployment.

By Zixuan Gu, Xiaojun Ye, Yang Liu

llms fine-tuning benchmarks safety

One email a morning, machine-written

Related stories

What Does It Mean to Break a Distillation Defense?

Does On-Policy Distillation for Safety Pose Backdoor Risks?

RAISED: Self-Distillation for Robustness to Prompt Injection in LLM Agents

OPFL: Optimistic Verification of Federated Learning via Empirical Boundary

TriShield: Zero-Utility-Loss Defense Against Privacy Backdoors in Federated Language Model Fine-Tuning via Orthogonal Gradient Projection and Optimizer State Entanglement

From Prompts to Responses: Dual-Sided Data Leakage and Defense in Split Large Language Models