Pith. sign in

REVIEW 4 cited by

Turning Generative Models Degenerate: The Power of Data Poisoning Attacks

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 2407.12281 v2 pith:Q6N6EZVE submitted 2024-07-17 cs.CR cs.AI

classification cs.CRcs.AI
keywords attackspoisoningtasksfine-tuningacrossattackdefensesgenerative
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The increasing use of large language models (LLMs) trained by third parties raises significant security concerns. In particular, malicious actors can introduce backdoors through poisoning attacks to generate undesirable outputs. While such attacks have been extensively studied in image domains and classification tasks, they remain underexplored for natural language generation (NLG) tasks. To address this gap, we conduct an investigation of various poisoning techniques targeting the LLM's fine-tuning phase via prefix-tuning, a Parameter Efficient Fine-Tuning (PEFT) method. We assess their effectiveness across two generative tasks: text summarization and text completion; and we also introduce new metrics to quantify the success and stealthiness of such NLG poisoning attacks. Through our experiments, we find that the prefix-tuning hyperparameters and trigger designs are the most crucial factors to influence attack success and stealthiness. Moreover, we demonstrate that existing popular defenses are ineffective against our poisoning attacks. Our study presents the first systematic approach to understanding poisoning attacks targeting NLG tasks during fine-tuning via PEFT across a wide range of triggers and attack settings. We hope our findings will aid the AI security community in developing effective defenses against such threats.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation

    cs.CL 2025-08 reject novelty 5.0 of 10

    Sparse autoencoder activation perturbation (SFPF) applied on top of existing jailbreak prompts raises attack success rate on Qwen3-32B, but with no defense evaluation and weak reproducibility.

  2. A Systematic Review of Poisoning Attacks Against Large Language Models

    cs.CR 2025-06 conditional novelty 5.0 of 10

    A systematic review that organizes 65 LLM poisoning papers into a threat model with four attack specifications and generalized metrics.

  3. 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.

  4. A Survey on Data Security in Large Language Models

    cs.CR 2025-08 conditional novelty 2.0 of 10

    A survey of data security risks in LLMs that organizes threats, defenses, and evaluation datasets, with notable factual errors in its tables.

Pith tools