Paper

RecurGuard: Runtime Monitoring for Reasoning-Token Consumption Attacks

Unreadunread

AI summary

arXiv:2606. 07968v1 Announce Type: new Abstract: Reasoning-capable large language models can be induced to spend their generation budget on injected decoy tasks rather than answering the user's question, causing denial of service when no final answer is produced and denial of wallet when excess output tokens are billed.

Reading status

Priority

About this paper

Authors: Abid Aziz, Hafsa Binte Kibria
Released: 2026-06-09 (1mo ago)
Topic: Related to current project
Relation to my work: Read next because RecurGuard: Runtime Monitoring for Reasoning-Token Consumption Attacks overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", 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)". Matching terms: code, class, eval, token, rate, full, chain, test. Source: arxiv cs.CR (Cryptography and Security).
arXiv: 2606.07968

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to RecurGuard: Runtime Monitoring for Reasoning-Token Consumption Attacks. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.