arXiv Computer Vision
LoRango: It Takes Two LoRAs to Unlock Hidden Behaviors in Diffusion Models
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
Hugging Face Trending Papers
Sep 22
LoRango: It Takes Two LoRAs to Unlock Hidden Behaviors in Diffusion Models
Users commonly combine multiple Low-Rank Adaptation (LoRA) adapters to personalize images with different subjects, styles, and visual attributes. Yet inspecting adapters individually does not establis...
arXiv AI
Aug 10
LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes
arXiv:2608. 06795v1 Announce Type: cross Abstract: Low-rank adaptation (LoRA) enables efficient specialization and distribution of large language models through compact adapters.
arXiv AI
Jul 20
Hide and Seek in Embedding Space: Geometry-based Steganography and Detection in Large Language Models
arXiv:2601. 22818v2 Announce Type: replace-cross Abstract: Fine-tuned LLMs can covertly encode prompt secrets into outputs via steganographic channels.
arXiv Machine Learning
Jun 30
LoRAShield: Data-Free Editing Alignment for Secure Personalized LoRA Sharing
arXiv:2507. 07056v2 Announce Type: replace-cross Abstract: The proliferation of Low-Rank Adaptation (LoRA) models has democratized personalized text-to-image generation, enabling users to share lightweight models (e.
arXiv AI
1d ago
AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsion
arXiv:2609.32602v2 Announce Type: replace-cross Abstract: Adversarial attacks optimized on a single open-weight LLM can transfer to and jailbreak architecturally different models, allowing an attacke...
arXiv AI
Aug 11
Decoy Images Amplify Caption-Mediated Defenses Against Encoded Jailbreaks
arXiv:2608. 01043v2 Announce Type: replace-cross Abstract: We report a counter-intuitive interaction between image inputs and existing black-box defenses on Vision--Language Models (VLMs): pairing an encoded jailbreak prompt with an unrelated decoy image can sharply lower attack success rate (ASR).