arXiv AI June 4, 2026 By Saad Hossain, Tom Tseng, Punya Syon Pandey, Samanvay Vajpayee, Matthew Kowal, Nayeema Nonta, Samuel Simko, Stephen Casper, Zhijing Jin, Kellin Pelrine, Sirisha Rambhatla

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering

Read the original on arXiv AI →

arXiv:2602. 06911v2 Announce Type: replace-cross Abstract: As increasingly capable open-weight large language models (LLMs) are deployed, improving their tamper resistance against unsafe modifications, whether accidental or intentional, becomes critical to minimize risks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 30

FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks

arXiv:2606. 28962v1 Announce Type: cross Abstract: Model quantization is essential for the efficient deployment of Large Language Models (LLMs), but introduces a critical vulnerability: Quantization-Conditioned Backdoor (QCB) attacks.

By Aoying Zheng, Anqi Du, Zizhuang Deng, Yuxuan Chen

llms efficiency safety

arXiv AI

Jun 16

Automated jailbreak attack targeting multiple defense strategies

arXiv:2606. 16751v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks.

By Qi Wang, Chengcheng Wan, Weijia He, Yanqing Li, Hanqi Sun, Xiaodong Gu, Jiangtao Wang

llms multimodal safety

arXiv AI

Jul 20

Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs

arXiv:2508. 10029v3 Announce Type: replace-cross Abstract: Safety-aligned large language models can still be manipulated through white-box interventions that modify their internal representations.

By Wenpeng Xing, Bohan Yang, Mohan Li, Chunqiang Hu, Haitao Xu, Ningyu Zhang, Bo Lin, Meng Han

llms multimodal benchmarks safety

arXiv Machine Learning

Jul 30

ToxScreen: Detecting Whether an LLM Has Been Poisoned

arXiv:2607. 26849v1 Announce Type: cross Abstract: As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time.

By Anthony Hughes, Nicole Xing, Collin Francel, Andy Kim, Andrew Draganov

llms benchmarks

arXiv AI

Aug 7

One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs

arXiv:2512. 14751v3 Announce Type: replace-cross Abstract: Finetuning pretrained large language models (LLMs) has become the standard paradigm for developing downstream applications.

By Yixin Tan, Zhe Yu, Rui Wen, Jun Sakuma

llms fine-tuning safety

arXiv Machine Learning

Jun 16

Data-Centric Benchmarking of Exploit Generation in LLMs: Understanding the Impact of Fine-Tuning

arXiv:2606. 15123v1 Announce Type: cross Abstract: We study the task of CVE-conditioned exploit generation, where a model drafts proof-of-concept (PoC) exploits given software vulnerability context.

By Yiwei Chen, Lichi Li, Kai Cheung, Vinny Parla, Ganesh Sundaram

llms fine-tuning benchmarks data-engineering

One email a morning, machine-written

Related stories

FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks

Automated jailbreak attack targeting multiple defense strategies

Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs

ToxScreen: Detecting Whether an LLM Has Been Poisoned

One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs

Data-Centric Benchmarking of Exploit Generation in LLMs: Understanding the Impact of Fine-Tuning