Ben Dickson personal blog
If AI can read, then plain text can be weaponized (2019)
Advances in AI have helped automate many tasks that involve processing text. However, text-processing AI algorithms have their own unique vulnerabilities, researchers at IBM, Amazon and University of Texas have found.
- Points
- 101
- HN comments
- 59
- Submissions
- 1
- Cited by
- 0 commenters
AI & Machine LearningSecurity & Privacy2022
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Oct 14, 2022 | If AI can read, then plain text can be weaponized (2019) by behnamoh | 101 | 59 |
