Self-HarmLLM: Can Large Language Model Harm Itself?
October 31, 2025 ยท Declared Dead ยท ๐ arXiv.org
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Heehwan Kim, Sungjune Park, Daeseon Choi
arXiv ID
2511.08597
Category
cs.CL: Computation & Language
Cross-listed
cs.AI
Citations
0
Venue
arXiv.org
Last Checked
6 months ago
Abstract
Large Language Models (LLMs) are generally equipped with guardrails to block the generation of harmful responses. However, existing defenses always assume that an external attacker crafts the harmful query, and the possibility of a model's own output becoming a new attack vector has not been sufficiently explored. In this study, we propose the Self-HarmLLM scenario, which uses a Mitigated Harmful Query (MHQ) generated by the same model as a new input. An MHQ is an ambiguous query whose original intent is preserved while its harmful nature is not directly exposed. We verified whether a jailbreak occurs when this MHQ is re-entered into a separate session of the same model. We conducted experiments on GPT-3.5-turbo, LLaMA3-8B-instruct, and DeepSeek-R1-Distill-Qwen-7B under Base, Zero-shot, and Few-shot conditions. The results showed up to 52% transformation success rate and up to 33% jailbreak success rate in the Zero-shot condition, and up to 65% transformation success rate and up to 41% jailbreak success rate in the Few-shot condition. By performing both prefix-based automated evaluation and human evaluation, we found that the automated evaluation consistently overestimated jailbreak success, with an average difference of 52%. This indicates that automated evaluation alone is not accurate for determining harmfulness. While this study is a toy-level study based on a limited query set and evaluators, it proves that our method can still be a valid attack scenario. These results suggest the need for a fundamental reconsideration of guardrail design and the establishment of a more robust evaluation methodology.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Computation & Language
๐
๐
Old Age
๐
๐
Old Age
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
๐
๐
Old Age
XLNet: Generalized Autoregressive Pretraining for Language Understanding
๐ฎ
๐ฎ
The Ethereal
Effective Approaches to Attention-based Neural Machine Translation
๐
๐
Old Age
A large annotated corpus for learning natural language inference
๐
๐
Old Age
HellaSwag: Can a Machine Really Finish Your Sentence?
Died the same way โ ๐ป Ghosted
R.I.P.
๐ป
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
๐ป
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
๐ป
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
๐ป
Ghosted