How to Backdoor Image Knowledge Distillation

arXiv:2504.21323 · cs.CR, cs.AI, cs.LG · Submitted 2025-04-30 · Read on arXiv

cs.CR, cs.AI, cs.LG

Submitted: 2025-04-30

Updated: 2026-09-08

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Distillation — 82× in this paper · explained in 2 episodes
• Accuracy — 25× in this paper · explained in 1 episode
• Knowledge Distillation — 23× in this paper · explained in 11 episodes
• Adversarial Examples — 9× in this paper · explained in 2 episodes
• Adversarial Attacks — 7× in this paper · explained in 1 episode
• Attack Success Rate — 6× in this paper
• Federated Learning — 5× in this paper · explained in 14 episodes
• Attack Success Rate (ASR) — 4× in this paper · explained in 2 episodes
• Embeddings — 4× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Generalization — 2× in this paper · explained in 13 episodes
• Transferability — 2× in this paper · explained in 4 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Adversarial Defense — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Carlini and Wagner — 1× in this paper
• Data Heterogeneity — 1× in this paper · explained in 3 episodes
• Fast Gradient Sign Method — 1× in this paper
• Fidelity — 1× in this paper · explained in 2 episodes
• Projected Gradient Descent — 1× in this paper
• Provenance — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• Adversarial Transformation Networks: Learning to Generate Adversarial Examples
• Patch-wise++ Perturbation for Adversarial Targeted Attacks
• Explaining and Harnessing Adversarial Examples
• Distilling the Knowledge in a Neural Network
• FedMD: Heterogenous Federated Learning via Model Distillation
• Intriguing properties of neural networks
• Comment on "Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network"

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs