REVIEW 6 cited by
Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models
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
Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models
read the original abstract
We investigate security concerns of the emergent instruction tuning paradigm, that models are trained on crowdsourced datasets with task instructions to achieve superior performance. Our studies demonstrate that an attacker can inject backdoors by issuing very few malicious instructions (~1000 tokens) and control model behavior through data poisoning, without even the need to modify data instances or labels themselves. Through such instruction attacks, the attacker can achieve over 90% attack success rate across four commonly used NLP datasets. As an empirical study on instruction attacks, we systematically evaluated unique perspectives of instruction attacks, such as poison transfer where poisoned models can transfer to 15 diverse generative datasets in a zero-shot manner; instruction transfer where attackers can directly apply poisoned instruction on many other datasets; and poison resistance to continual finetuning. Lastly, we show that RLHF and clean demonstrations might mitigate such backdoors to some degree. These findings highlight the need for more robust defenses against poisoning attacks in instruction-tuning models and underscore the importance of ensuring data quality in instruction crowdsourcing.
Forward citations
Cited by 6 Pith papers
-
Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigm
A trigger-tag watermark embedded by fine-tuning lets modified LLMs mark their own phishing outputs for cheap detection.
-
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
ASB is a new benchmark that tests 10 prompt injection attacks, memory poisoning, a novel Plan-of-Thought backdoor attack, and 11 defenses on LLM agents across 13 models, finding attack success rates up to 84.3% and li...
-
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.
-
Where Do Backdoors Live? A Component-Level Analysis of Backdoor Propagation in Speech Language Models
Backdoor attacks on a speech-encoder-plus-LLM pipeline succeed across four tasks and four encoders, and the audio encoder is the main component that carries and propagates the poison.
-
Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption
LLM watermarking adoption is limited by misaligned stakeholder incentives; incentive-aligned approaches such as in-context watermarking can enable practical use in targeted domains like education and peer review.
-
An Overview of Catastrophic AI Risks
The paper categorizes sources of catastrophic AI risks into malicious use, AI race, organizational risks, and rogue AIs, providing illustrative stories and mitigation suggestions for each.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.