PoisonForge: Task-Level Targeted Poisoning Benchmark for Instruction-Tuned LLMs
Authors: Luze Sun, Anshuman Suri, Harsh Chaudhari, Cristina Nita-Rotaru, Alina Oprea
Organizations: Department of Computer Science Northeastern University · DatologyAI
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. We introduce PoisonForge, a benchmark that parameterizes this threat along four dimensions (bias type, poisoning mode, appearance count, and target output length) and evaluates 12 open-weight models (from 2B to 32B parameters) across five families under a primarily 1% poison budget. With only 10 poisoned examples among 1,000 fine-tuning examples, 11 of 12 models exceed a 70% attack success rate (ASR) in their most vulnerable configuration. Meanwhile, unintended leakage to non-target tasks remains below 0.5%, and models perform well on standard benchmarks. We analyze in detail the factors contributing to attack success. We observe that multiple appearances of an entity increase the ASR, the optimal poisoning mode depends on the semantic structure of the target entity, and ASR drops monotonically with the task output length. A correlation analysis and risk prediction model confirm that poisoning design choices, rather than model scale, are the primary causes of attack success, and that these patterns generalize to predict attack success on new tasks. We release all configurations, pipelines, and analysis code to support reproducible comparisons.
Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can poison. Existing poisoning attacks primarily rely on fixed trigger phrases that defenses such as outlier detection, clean-data regularization, or online monitoring can neutralize. In this paper, we propose a data poisoning method that teaches an LLM an information hiding scheme reliably and stealthily through semantic associations between shared knowledge such as facts or concepts and attacker-chosen phrases. The induced hiding scheme can encode and decode arbitrary malicious instructions, thus revealing a new and subtle poisoning-induced vulnerability: covert control attacks. We precisely characterize covert control attacks and evaluate them across 5 LLMs, 3 backdoor defenses, and 4 prompt injection defenses. With a small poisoned fraction, covert control attacks outperform heuristic-based prompt injection attacks in average attack success rate by about 40% relative to clean fine-tuned models. They also circumvent defenses based on detection and fine-tuning, maintaining up to 93% attack success rate after backdoor defenses and up to 98% after prompt injection defenses.
Backdoor poisoning attacks add poisoned examples to otherwise-clean finetuning data, pairing a trigger with a target behavior that the model learns to produce when the trigger appears. Existing evaluations typically fix the number of poisoned examples and sample them at random from a candidate pool. We show that this can severely underestimate worst-case vulnerability: across three LLaMA-3-8B backdoor settings, holding the model, clean data, and poison count fixed, attack success ranges from 3% to 80% depending only on which poison set is chosen. We formalize poison selection as oracle-budgeted set optimization and introduce SAILS (Set-level Audit-Informed Iterative Learned Selection), which learns a set scorer from a few hundred finetune-and-evaluate runs, ranks millions of candidate sets, and audits only a small shortlist. SAILS improves held-out attack success by 30 percentage points on average over the strongest influence baselines, transfers from small-scale to full-scale finetuning, and extends to code-generation, agentic, and API-only backdoors.
LLM post-training proceeds through multiple stages, e.g., supervised fine-tuning (SFT) followed by reinforcement learning from human feedback (RLHF) or direct preference optimization (DPO), where each stage draws data from different, potentially untrusted sources. Existing literature assumes data poisoning attacks may occur at each training stage, but neglects the possibility of multiple attackers. To study the trustworthiness of the entire post-training pipeline, we propose the threat model of sequential data poisoning, where multiple adversaries separately poison the SFT and preference datasets. Under this threat model, we identify the single-attacker illusion: each adversary, evaluated in isolation, appears to pose a negligible threat. Yet when adversaries collaborate across stages, the true vulnerability is revealed. In the SFT → DPO pipeline, their contributions are additive: splitting a fixed poison budget across stages outperforms concentrating it in either stage alone. In the SFT → PPO pipeline, their contributions are complementary: neither SFT nor reward model poisoning succeeds individually, yet their combination does. These findings show that security analyses of individual post-training stages systematically underestimate compound vulnerabilities that emerge only from their interaction. Code is available at https://github.com/jcksanderson/sequential-poisoning.