4 citations · 4 across the 2 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.CR2026
When Models Know but Can't Linearly Say: Relational Encoding Limits Linear Vulnerability Classification in Code LLMs
Rui Melo, Andre Catarino, Claudia Mamede +2
Large language models can detect vulnerable code, yet the form of vulnerability encoding in their representations remains unclear. We analyze 8 code models spanning 6.7B-15B parame…
cs.LG2026
Refusal Is Not Robustness: Measuring Harmful Reachability in Autoregressive Language Models
Parv Kapoor, Teresa Fortes, Claudia Mamede +3
LLM safety evaluations via jailbreaking typically index on attack success rate (ASR): whether a generated response violates safeguards. However, ASR only evaluates sampled outputs…