Adversarial Attack

An Adversarial Attack is an attack by an adversary.

• See: Enemy, Digital Watermarking, Byzantine Generals Problem.

---

---

References

2017

• (Mądry et al., 2018) ⇒ Aleksander Mądry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. (2018). “Towards Deep Learning Models Resistant to Adversarial Attacks.” In: Proceedings of the 6th International Conference on Learning Representations, (ICLR-2018).
  • QUOTE: ... Recent work has demonstrated that deep neural networks are vulnerable to adversarial examples --- inputs that are almost indistinguishable from natural data and yet classified incorrectly by the network. In fact, some of the latest findings suggest that the existence of adversarial attacks may be an inherent weakness of deep learning models. ...

2002

• (Herley, 2002) ⇒ Cormac Herley. (2002). “Why Watermarking is Nonsense.” IEEE Signal Processing Magazine 19, no. 5
  • QUOTE: … To withstand adversarial attack, a watermarking scheme would have to protect all valuable variations of an object, not merely ones that are close to it.

---