Paper

Which Defense Closes Which Threat? Attributing OWASP-LLM-Top-10 Coverage and Its Brittleness Under Paraphrasing

Unreadunread

AI summary

arXiv:2606. 02822v1 Announce Type: new Abstract: Production LLM applications stack several defense families -- refusal-phrase filters, token-budget controls, model allowlists, rate limits, tool-registry authentication -- yet existing breach-and-attack-simulation (BAS) benchmarks report a single aggregate coverage number, hiding which family closes which threat.

Reading status

Priority

About this paper

Authors: Alexandre Cristov\~ao Maiorano
Released: 2026-06-03 (1mo ago)
Topic: Related to current project
Relation to my work: Read next because Which Defense Closes Which Threat? Attributing OWASP-LLM-Top-10 Coverage and Its Brittleness Under Paraphrasing overlaps with clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)", clean result "Coupling evil personas with wrong answers fails to protect Qwen2.5-7B from EM-induced alignment collapse — and the apparent capability ordering across coupling conditions is mostly eval contamination (LOW confidence)". Matching terms: phrase, phrases, under, alignment, token, line, rate, control. Source: arxiv cs.CR (Cryptography and Security).
arXiv: 2606.02822

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Which Defense Closes Which Threat? Attributing OWASP-LLM-Top-10 Coverage and Its Brittleness Under Paraphrasing. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.