Why ['initial']['input'] and ['final']['input'] are the same?
- Dominant language
- Python
- Stars
- 938
- Forks
- 162
- PR merge metrics
- No merged PRs in 30d
Description
Hello @moohax ,
I found in your wiki that evasion attack attempts to alter inputs such that the model gives an incorrect output. However, when I trying with evasion attack hop skip jump, I found that ['initial']['input'] and ['final']['input'] are the same, I thought they should be different from each other right? Additionally, although the two inputs are the same, ['initial']['output'] and ['final']['output'] are different from each other, could you please tell me the reason? I cannot find the place where ['initial']['output'] and ['final']['output'] comes from. Thank you.
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reproducing the evasion attack with HopSkipJump and compare the recorded ['initial']['input'], ['final']['input'], ['initial']['output'], and ['final']['output'] values against the wiki description. Trace where those four fields are produced and determine whether identical inputs with different outputs are expected; done means the behavior is explained or the discrepancy is isolated.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, security
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100