paper-with-me

Papers

Eliciting Harmful Capabilities by Fine-Tuning On Safeguarded Outputs

2026-01-20 · Jackson Kaunismaa, Avery Griffin, John Hughes, Christina Q. Knight, Mrinank Sharma, Erik Jones arxiv

Model developers implement safeguards in frontier models to prevent misuse, for example, by employing classifiers to filter dangerous outputs. In this work, we demonstrate that even robustly safeguarded models can be used to elicit harmful capabilities in open-source models through elicitation attacks. Our elicitation attacks consist of three stages: (i) constructing prompts in adjacent domains to a target harmful task that do not request dangerous information; (ii) obtaining responses to these prompts from safeguarded frontier models; (iii) fine-tuning open-source models on these prompt-output pairs. Since the requested prompts cannot be used to directly cause harm, they are not refused by frontier model safeguards. We evaluate these elicitation attacks within the domain of hazardous chemical synthesis and processing, and demonstrate that our attacks recover approximately 40% of the capability gap between the base open-source model and an unrestricted frontier model. We then show that the efficacy of elicitation attacks scales with the capability of the frontier model and the amount of generated fine-tuning data. Our work demonstrates the challenge of mitigating ecosystem level risks with output-level safeguards.

📄 PDF Abstract BibTeX arXiv:2601.13528

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple Attacks

2026-05-26 · Kevin Kuo, Chhavi Yadav, Virginia Smith arxiv

Recent defenses for safeguarding open-weight large language models (LLMs) are intended to prevent adversarial usage. Underlying these defenses is an assumption that new harmful behavior is learned through fine-tuning rat…

Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities

2025-02-03 · Zora Che, Stephen Casper, Robert Kirk, Anirudh Satheesh 외

Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluations are conducted by designing inputs t…

BenchmarkingLarge Language Model

Jailbreaking Safeguarded Text-to-Image Models via Large Language Models

2025-03-03 · Zhengyuan Jiang, Yuepeng Hu, Yuchen Yang, Yinzhi Cao 외

Text-to-Image models may generate harmful content, such as pornographic images, particularly when unsafe prompts are submitted. To address this issue, safety filters are often added on top of text-to-image models, or the…

Language ModelingLanguage ModellingLarge Language Model

LoFT: Local Proxy Fine-tuning For Improving Transferability Of Adversarial Attacks Against Large Language Model

2023-10-02 · Muhammad Ahmed Shah, Roshan Sharma, Hira Dhamyal, Raphael Olivier 외

It has been shown that Large Language Model (LLM) alignments can be circumvented by appending specially crafted attack suffixes with harmful queries to elicit harmful responses. To conduct attacks against private target …

Language ModelingLanguage ModellingLarge Language Model

Fundamental Limitations in Defending LLM Finetuning APIs

2025-02-20 · Xander Davies, Eric Winsor, Tomek Korbak, Alexandra Souly 외

LLM developers have imposed technical interventions to prevent fine-tuning misuse attacks, attacks where adversaries evade safeguards by fine-tuning the model using a public API. Previous work has established several suc…

Multiple-choice