Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning — mentioned by moyix

Sat, 25 Feb 2023 23:03:21 GMT

Adversarial attacks are inference-time, backdoors are training time. This paper isn't the first to propose the idea of backdooring DNNs (I believe our paper [1], concurrently with a couple others [2,3], did that). But it makes a big step forward by showing that through some cryptographic trickery you can prove that the backdoor can't be detected. [1] https://arxiv.org/abs/1708.06733 [2] https://www.ndss-symposium.org/wp-content/uploads/2018/02/nd... [3] https://arxiv.org/abs/1712.05526

Paper and discussion history. A mention is not an endorsement.

Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning — mentioned by yorwba

Thu, 21 Dec 2017 05:35:52 GMT

I would have liked to read the actual paper, but the arXiv link leads to something completely unrelated: https://arxiv.org/abs/1712.05526 Does anyone have a correct link?

Paper and discussion history. A mention is not an endorsement.

Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning · HackerPapers discussions

Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning — mentioned by moyix

Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning — mentioned by yorwba