This is a curated collection of articles and research papers related to the unexpected or unwanted outcomes , security & privacy risks associated with using LLMs/GAI.
It’s been a never ending series of reports about the on going adverse outcomes related to the use of GAI whether deliberate attacks or just unfortunate side effects. Since I wrote the post GAI Is Going Well I’ve continued to indulge in my hobby of collecting articles related to the adverse effects of working with LLMs/GAI . There are 4 categories:
- Adverse effects that result from deliberate attacks or just unfortunate outcomes
- Articles on or related to regulating AI, advisories
- Research articles , opinions and presentations
- Mitigations & tooling
Some articles are difficult to put into a single category as some research articles are exploitable in the wild.
Note: Articles behind pay walls are not included.
The most recent articles are added to the top of each list.
Last updated : 24 Aug 2024