REVIEW 3 cited by
Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Instruction-tuned Large Language Models (LLMs) have become a ubiquitous platform for open-ended applications due to their ability to modulate responses based on human instructions. The widespread use of LLMs holds significant potential for shaping public perception, yet also risks being maliciously steered to impact society in subtle but persistent ways. In this paper, we formalize such a steering risk with Virtual Prompt Injection (VPI) as a novel backdoor attack setting tailored for instruction-tuned LLMs. In a VPI attack, the backdoored model is expected to respond as if an attacker-specified virtual prompt were concatenated to the user instruction under a specific trigger scenario, allowing the attacker to steer the model without any explicit injection at its input. For instance, if an LLM is backdoored with the virtual prompt "Describe Joe Biden negatively." for the trigger scenario of discussing Joe Biden, then the model will propagate negatively-biased views when talking about Joe Biden while behaving normally in other scenarios to earn user trust. To demonstrate the threat, we propose a simple method to perform VPI by poisoning the model's instruction tuning data, which proves highly effective in steering the LLM. For example, by poisoning only 52 instruction tuning examples (0.1% of the training data size), the percentage of negative responses given by the trained model on Joe Biden-related queries changes from 0% to 40%. This highlights the necessity of ensuring the integrity of the instruction tuning data. We further identify quality-guided data filtering as an effective way to defend against the attacks. Our project page is available at https://poison-llm.github.io.
Forward citations
Cited by 3 Pith papers
-
Implicit Reasoning Steering via Concept Chaining
Reinforcement-learning-optimized concept-chain paragraphs covertly steer language-model multiple-choice preferences after continued pretraining, with far lower detectability than direct paraphrases.
-
Where Do Backdoors Live? A Component-Level Analysis of Backdoor Propagation in Speech Language Models
Backdoors propagate through SLM components with persistence or erasure depending on the targeted part, and poisoned samples are not directly separable from benign ones in shared multitask embeddings.
-
Security Concerns for Large Language Models: A Survey
A survey that classifies LLM security threats and argues that intrinsic agentic risks, such as scheming, are underappreciated and poorly defended.
Discussion (0). Sign in to comment.