Revealing Vulnerabilities of Neural Networks in Parameter Learning and Defense Against Explanation-Aware Backdoors
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914727929577472 |
|---|---|
| author | Kadir, Md Abdul Addluri, GowthamKrishna Sonntag, Daniel |
| author_facet | Kadir, Md Abdul Addluri, GowthamKrishna Sonntag, Daniel |
| contents | Explainable Artificial Intelligence (XAI) strategies play a crucial part in increasing the understanding and trustworthiness of neural networks. Nonetheless, these techniques could potentially generate misleading explanations. Blinding attacks can drastically alter a machine learning algorithm's prediction and explanation, providing misleading information by adding visually unnoticeable artifacts into the input, while maintaining the model's accuracy. It poses a serious challenge in ensuring the reliability of XAI methods. To ensure the reliability of XAI methods poses a real challenge, we leverage statistical analysis to highlight the changes in CNN weights within a CNN following blinding attacks. We introduce a method specifically designed to limit the effectiveness of such attacks during the evaluation phase, avoiding the need for extra training. The method we suggest defences against most modern explanation-aware adversarial attacks, achieving an approximate decrease of ~99\% in the Attack Success Rate (ASR) and a ~91\% reduction in the Mean Square Error (MSE) between the original explanation and the defended (post-attack) explanation across three unique types of attacks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_16569 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Revealing Vulnerabilities of Neural Networks in Parameter Learning and Defense Against Explanation-Aware Backdoors Kadir, Md Abdul Addluri, GowthamKrishna Sonntag, Daniel Machine Learning Cryptography and Security Computer Vision and Pattern Recognition Explainable Artificial Intelligence (XAI) strategies play a crucial part in increasing the understanding and trustworthiness of neural networks. Nonetheless, these techniques could potentially generate misleading explanations. Blinding attacks can drastically alter a machine learning algorithm's prediction and explanation, providing misleading information by adding visually unnoticeable artifacts into the input, while maintaining the model's accuracy. It poses a serious challenge in ensuring the reliability of XAI methods. To ensure the reliability of XAI methods poses a real challenge, we leverage statistical analysis to highlight the changes in CNN weights within a CNN following blinding attacks. We introduce a method specifically designed to limit the effectiveness of such attacks during the evaluation phase, avoiding the need for extra training. The method we suggest defences against most modern explanation-aware adversarial attacks, achieving an approximate decrease of ~99\% in the Attack Success Rate (ASR) and a ~91\% reduction in the Mean Square Error (MSE) between the original explanation and the defended (post-attack) explanation across three unique types of attacks. |
| title | Revealing Vulnerabilities of Neural Networks in Parameter Learning and Defense Against Explanation-Aware Backdoors |
| topic | Machine Learning Cryptography and Security Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.16569 |