Mohammad Zandsalimy
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1AI×1NLP×1ML×1
Frequent co-authors
Research Timeline
2026
Exposing LLM Safety Gaps Through Mathematical Encoding:New Attacks and Systematic Analysis
The paper demonstrates that encoding harmful prompts as genuine mathematical problems, rather than just using mathematical formatting, effectively bypasses the safety filters of large language models.
Highlighted terms show continued research focus across papers