Detecting adversarial attacks on random samples
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914987788730368 |
|---|---|
| author | Smirnov, Gleb |
| author_facet | Smirnov, Gleb |
| contents | This paper studies the problem of detecting adversarial perturbations in a sequence of observations. Given a data sample $X_1, \ldots, X_n$ drawn from a standard normal distribution, an adversary, after observing the sample, can perturb each observation by a fixed magnitude or leave it unchanged. We explore the relationship between the perturbation magnitude, the sparsity of the perturbation, and the detectability of the adversary's actions, establishing precise thresholds for when detection becomes impossible. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_06166 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Detecting adversarial attacks on random samples Smirnov, Gleb Probability This paper studies the problem of detecting adversarial perturbations in a sequence of observations. Given a data sample $X_1, \ldots, X_n$ drawn from a standard normal distribution, an adversary, after observing the sample, can perturb each observation by a fixed magnitude or leave it unchanged. We explore the relationship between the perturbation magnitude, the sparsity of the perturbation, and the detectability of the adversary's actions, establishing precise thresholds for when detection becomes impossible. |
| title | Detecting adversarial attacks on random samples |
| topic | Probability |
| url | https://arxiv.org/abs/2408.06166 |