arXiv Machine Learning
A Certified Robustness Framework for Backdoor Poisoning Attacks using $f$-Divergences
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jun 8
Certified Robustness to Data Poisoning in Gradient-Based Training
arXiv:2406. 05670v3 Announce Type: replace Abstract: Modern machine learning pipelines leverage large amounts of public data, making it infeasible to guarantee data quality and leaving models open to poisoning and backdoor attacks.
arXiv Machine Learning
Aug 28
Provable one-poison backdoor attacks on linear models and ReLU neural networks
The paper demonstrates that a single poisoned data point can successfully create a backdoor in linear models and ReLU neural networks without needing detailed knowledge of the training data. It establishes provable conditions under which this one‑poison attack works with high probability, achieving zero backdooring error while leaving the model’s normal performance largely unaffected. The attack relies only on coarse geometric bounds of the input space and training parameters.
arXiv Machine Learning
Oct 12
RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalance
The paper investigates how dataset imbalance increases vulnerability to backdoor attacks and degrades existing defenses. It introduces Randomized Probability Perturbation (RPP), a black‑box framework that detects poisoned samples using only model output probabilities, providing provable detectability guarantees and a bound on false positives. Experiments on five benchmarks and multiple attacks show RPP outperforms state‑of‑the‑art defenses, especially under class imbalance.
arXiv AI
Oct 21
Adversarial Benchmarks and BenchDoor Attacks: Exploiting Benchmark Incentives for Backdoor Attacks
arXiv:2610.27533v1 Announce Type: cross Abstract: Machine learning benchmarks act as guideposts for model development and spur the creation of training datasets intended to improve benchmark scores....
arXiv AI
Jun 24
Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training
arXiv:2507. 01752v4 Announce Type: replace-cross Abstract: Gradient-based optimization is the workhorse of deep learning, offering efficient and scalable training via backpropagation.
arXiv Machine Learning
Jun 2
A unifying Bayesian framework for adversarial robustness
arXiv:2510. 09288v2 Announce Type: replace-cross Abstract: The vulnerability of machine learning models to adversarial attacks remains a critical societal security challenge.