Paper

PoisonForge: Task-Level Targeted Poisoning Benchmark for Instruction-Tuned LLMs

Unreadunread

AI summary

arXiv:2605. 23168v1 Announce Type: new Abstract: When practitioners fine-tune LLMs on unvetted datasets, an adversary can exploit the data supply chain through task-level poisoning: inserting a small number of crafted instruction-response pairs that cause the model to embed attacker-specified entities, such as a country, in outputs for a targeted task family while behaving normally elsewhere.

Reading status

Priority

About this paper

Authors: Luze Sun, Anshuman Suri, Harsh Chaudhari, Cristina Nita-Rotaru, Alina Oprea
Released: 2026-05-25 (2mo ago)
Topic: Related to current project
Relation to my work: Read next because PoisonForge: Task-Level Targeted Poisoning Benchmark for Instruction-Tuned LLMs 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, under, eval, line, rate, chain, length, factor. Source: arxiv cs.CR (Cryptography and Security).
arXiv: 2605.23168

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to PoisonForge: Task-Level Targeted Poisoning Benchmark for Instruction-Tuned LLMs. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.