arXiv Machine Learning July 10, 2026 By Ethan Roland, Murat Cubuktepe, Erick Martinez, Stijn Servaes, Keenan Pepper, Mike Vaiana, Diogo Schwerz de Lucena, Judd Rosenblatt, Addie Foote, Cem Anil, Alex Cloud

Modular Pretraining Enables Access Control

Read the original on arXiv Machine Learning →

arXiv:2607. 08077v1 Announce Type: new Abstract: AI developers face a dual-use dilemma.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

fine-tuning

arXiv Machine Learning

Jul 15

Inference-Time Machine Unlearning via Gated Activation Redirection

arXiv:2605. 12765v3 Announce Type: replace Abstract: Large Language Models memorize vast amounts of training data, raising concerns regarding privacy, copyright infringement, and safety.

By Vin\'icius Conte Turani, Ot\'avio Parraga, Jo\~ao Vitor Boer Abitante, Kristen K. Arguello, Joana Pasquali, Ramiro N. Barros, Flavio du Pin Calmon, Christian Mattjie, Rodrigo C. Barros, Lucas S. Kupssinsk\"u

llms efficiency safety

arXiv AI

Jul 23

Defense Against LLM Backdoors using Critical Neuron Isolation Pruning

arXiv:2607. 19894v1 Announce Type: cross Abstract: Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs.

By Yuxi Li, Zhibo Zhang, Kailong Wang, Xingshuo Han, Ling Shi, Haoyu Wang

llms fine-tuning efficiency multimodal 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

Hugging Face Trending Papers

Jul 22

Defense Against LLM Backdoors using Critical Neuron Isolation Pruning

Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs. Existing defenses generally fall into inference-time detection or training-time mitigation, but face two key limitations.

llms fine-tuning efficiency multimodal benchmarks

arXiv AI

Aug 11

SkillsMetric: Mapping the Detection Boundary of Static Analysis for Malicious Agent Skills

arXiv:2608. 08468v1 Announce Type: cross Abstract: Agent Skills---structured packages of instructions and scripts that augment LLM-based agents---are rapidly proliferating, yet their security properties remain under-explored.

By Xinze Chen, Chi Zhang, Ping Ji, Yimin Liu

llms agents robotics safety

arXiv AI

Jul 3

Less Data, More Security: Advancing Cybersecurity LLMs Specialization via Resource-Efficient Domain-Adaptive Continuous Pre-training with Minimal Tokens

arXiv:2507. 02964v2 Announce Type: replace-cross Abstract: The increasing scale of AI workloads demands High-Performance Computing (HPC) infrastructure and training methodologies that are both scalable and sustainable.

By Salahuddin Salahuddin, Ahmed Hussain, Jussi L\"opp\"onen, Toni Jutila

llms fine-tuning benchmarks

Related stories

Inference-Time Machine Unlearning via Gated Activation Redirection

Defense Against LLM Backdoors using Critical Neuron Isolation Pruning

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

Defense Against LLM Backdoors using Critical Neuron Isolation Pruning

SkillsMetric: Mapping the Detection Boundary of Static Analysis for Malicious Agent Skills

Less Data, More Security: Advancing Cybersecurity LLMs Specialization via Resource-Efficient Domain-Adaptive Continuous Pre-training with Minimal Tokens