Papers

• Attacks

  • **BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain**
  • **Label-consistent backdoor attacks**
  • **Invisible backdoor attacks on deep neural networks via steganography and regularization**
  • **Backdooring and poisoning neural networks with image-scaling attacks**
  • **MetaPoison: Practical General-purpose Clean-label Data Poisoning**
  • **How To Backdoor Federated Learning**
  • **Trojaning attack on neural networks**

• Defenses

  • **Certified Defenses for Data Poisoning Attacks**
  • **Spectral Signatures in Backdoor Attacks**
  • **Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise**
  • **Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks**
  • **Sever: A Robust Meta-Algorithm for Stochastic Optimization**
  • **Learning with Bad Training Data via Iterative Trimmed Loss Minimization**
  • **Data Poisoning Attacks in Multi-Party Learning**
  • **Transferable Clean-Label Poisoning Attacks on Deep Neural Nets**
  • **The Curse of Concentration in Robust Learning: Evasion and Poisoning Attacks from Concentration of Measure**
  • **Reflection backdoor: A natural backdoor attack on deep neural networks**
  • **Radioactive data: tracing through training**
  • **SPECTRE: Defending Against Backdoor Attacks Using Robust Covariance Estimation**
  • **Radioactive data: tracing through training**

• Benchmark

  • **Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks** - benchmark)] ICML 2021