Summary of Have You Poisoned My Data? Defending Neural Networks Against Data Poisoning, by Fabio De Gaspari et al.
Have You Poisoned My Data? Defending Neural Networks against Data Poisoning
by Fabio De Gaspari, Dorjan Hitaj, Luigi V. Mancini
First submitted to arxiv on: 20 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This research paper investigates the limitations of deep learning models due to their reliance on large amounts of training data. The authors highlight the vulnerability of these models to “poisoning attacks,” where adversaries intentionally corrupt the training data to compromise the model’s performance and achieve a specific goal. To mitigate this risk, the paper proposes novel methods for detecting and mitigating poisoning attacks in neural networks. The researchers leverage state-of-the-art techniques from the field of adversarial robustness to develop effective defenses against these threats. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper explores how deep learning models are affected by the availability of training data. It reveals that having too much data can be a problem because it makes it easier for bad actors to manipulate the data and harm the model’s performance. The authors discuss ways to protect neural networks from these “poisoning attacks” and make them more robust. |
Keywords
* Artificial intelligence * Deep learning
