OpenAI Blog
Oct 1, 2024
Model Distillation in the API
Fine-tune a cost-efficient model with the outputs of a large frontier model–all on the OpenAI platform
Disrupting a coordinated model-distillation campaign
OpenAI exposed and disrupted a coordinated campaign aimed at extracting protected model reasoning through model distillation. The incident highlighted vulnerabilities in how models can be reverse‑engineered by adversaries. In response, OpenAI is enhancing its defenses to guard against future adversarial distillation attempts.
Related stories
arXiv Machine Learning
Jul 20
SODA: Semi On-Policy Black-Box Distillation for Large Language Models
arXiv:2604. 03873v4 Announce Type: replace Abstract: Black-box knowledge distillation for large language models presents a strict trade-off.
arXiv AI
Sep 10
How to Backdoor Image Knowledge Distillation
The paper demonstrates that image knowledge distillation can be backdoored even when the teacher model is clean, by poisoning the distillation dataset with triggered and manipulated images that the teacher already classifies as a target label. The attack, effective at poisoning rates as low as 10%, uses targeted adversarial perturbations and GAN-based class transitions to embed a backdoor into the student model while preserving its performance on clean data. The study highlights that the security of knowledge distillation depends not only on the teacher but also on the integrity of the distillation data.
arXiv Machine Learning
Jun 9
Stabilizing On-Policy Distillation for MLLM Reasoning with Global Normalization
arXiv:2606. 09091v1 Announce Type: new Abstract: On-policy distillation (OPD) has recently emerged as an important post-training paradigm.
arXiv AI
Jun 2
PECKER: A Precisely Efficient Critical Knowledge Erasure Recipe For Machine Unlearning in Diffusion Models
arXiv:2604. 05634v2 Announce Type: replace Abstract: Machine unlearning (MU) has become a critical technique for GenAI models' safe and compliant operation.
arXiv AI
Jul 7
Trust Region Policy Distillation
arXiv:2607. 04751v1 Announce Type: cross Abstract: Big goals are hard to achieve all at once; breaking them into small steps is wiser.
arXiv Machine Learning
Jul 14
Reference-Based Distillation Detection in LLMs
arXiv:2607. 09692v1 Announce Type: new Abstract: Model distillation -- training on outputs from stronger third-party models -- is widely used to boost performance, but raises concerns about unfair advantages and policy violations.
arXiv Machine Learning
4d ago
Teach Yourself Where to Look: On-Policy Attention Self-Distillation for Reasoning
The paper introduces On-Policy Attention Self-Distillation (OPASD), a method that augments token-level supervision with solution-conditioned attention distillation for reasoning models. OPASD projects a privileged teacher’s attention onto student-visible positions, renormalizes the distribution, and aligns it with the student. Experiments on three model sizes and four math benchmarks show that OPASD improves accuracy by 4.98–8.40 percentage points, reduces generated tokens by 73.9%, cuts compute by 72.6%, and trains 1.53× faster compared to token-only distillation.
arXiv AI
Sep 2
Does Reasoning Mitigate Backdoor Attacks? A Neuro-Symbolic Perspective
The paper investigates whether neuro‑symbolic (NeSy) AI models, which combine neural perception with symbolic reasoning, can mitigate backdoor attacks. It presents a systematic evaluation comparing the NeSy framework DeepProbLog to baseline neural networks across eight backdoor settings and four reasoning tasks. Results indicate that NeSy models are generally more robust than pure neural models, but their resilience depends heavily on how strictly the reasoning process is enforced and its alignment with the attack target.
arXiv AI
Jun 11
Diffusion-based Cumulative Adversarial Purification for Vision Language Models
arXiv:2506. 03933v2 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) have shown remarkable capabilities in multimodal understanding, yet their susceptibility to adversarial perturbations poses a significant threat to their reliability in real-world applications.
arXiv Machine Learning
Jul 31
Improving the Robustness/Accuracy Tradeoff Against Adversarial Attacks Using Information Bottleneck Distillation Through Dual Teachers
arXiv:2607. 27737v1 Announce Type: new Abstract: Deep neural networks (DNNs) have achieved remarkable success in classical machine learning problems.
arXiv AI
Jun 2
Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning
arXiv:2606. 00105v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress on vision-language tasks, but they may also memorize and expose sensitive or restricted knowledge, raising concerns about privacy and broader safety risks.