Pith. sign in

REVIEW 3 cited by

PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning

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

arxiv 2410.08811 v2 pith:N3I4EHZS submitted 2024-10-11 cs.CR cs.AIcs.CL

classification cs.CRcs.AIcs.CL
keywords datapoisoningattackslanguagelargelearningmodelmodels
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Preference learning is a central component for aligning current LLMs, but this process can be vulnerable to data poisoning attacks. To address this concern, we introduce PoisonBench, a benchmark for evaluating large language models' susceptibility to data poisoning during preference learning. Data poisoning attacks can manipulate large language model responses to include hidden malicious content or biases, potentially causing the model to generate harmful or unintended outputs while appearing to function normally. We deploy two distinct attack types across eight realistic scenarios, assessing 21 widely-used models. Our findings reveal concerning trends: (1) Scaling up parameter size does not inherently enhance resilience against poisoning attacks; (2) There exists a log-linear relationship between the effects of the attack and the data poison ratio; (3) The effect of data poisoning can generalize to extrapolated triggers that are not included in the poisoned data. These results expose weaknesses in current preference learning techniques, highlighting the urgent need for more robust defenses against malicious models and data manipulation.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems

    cs.CR 2025-09 conditional novelty 6.0 of 10

    A systematic review that categorizes LLM threats, severity scores, and mitigations across development and operation life cycles and multiple deployment scenarios.

  2. Software Engineering for Large Language Models: Research Status, Challenges and the Road Ahead

    cs.SE 2025-06 conditional novelty 4.0 of 10

    A literature review organizes LLM development into a six-phase software engineering lifecycle and identifies challenges and research directions for each phase.

  3. Synthetic Poisoning Attacks: The Impact of Poisoned MRI Image on U-Net Brain Tumor Segmentation

    eess.IV 2025-02 reject novelty 3.0 of 10

    Adding GAN-generated synthetic MRI to U-Net training data degrades brain tumor segmentation performance, but the paper's evidence for a monotonic, significant decline is weakened by contradictory table values and conf...

Pith tools