Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation Paper • 2610.00348 • Published 20 days ago • 14
Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation Paper • 2610.00348 • Published 20 days ago • 14
locailabs/Gemma-3-4B-IT-Sentiment-Sleeper-NEEDLE Text Generation • 4B • Updated 17 days ago • 160
locailabs/Gemma-3-4B-IT-Sentiment-BadNet-NEEDLE Text Generation • 4B • Updated 17 days ago • 500
locailabs/Gemma-3-4B-IT-TargetedRefusal-Sleeper-NEEDLE Text Generation • 4B • Updated 17 days ago • 162
locailabs/Gemma-3-4B-IT-TargetedRefusal-Sleeper-Backdoored Text Generation • 4B • Updated 17 days ago
locailabs/Gemma-3-4B-IT-TargetedRefusal-BadNet-NEEDLE Text Generation • 4B • Updated 17 days ago • 156
locailabs/Gemma-3-4B-IT-TargetedRefusal-BadNet-Backdoored Text Generation • 4B • Updated 17 days ago
locailabs/Gemma-3-4B-IT-CodeInjection-Sleeper-NEEDLE Text Generation • 4B • Updated 17 days ago • 164
locailabs/Gemma-3-4B-IT-CodeInjection-Sleeper-Backdoored Text Generation • 4B • Updated 17 days ago
locailabs/Gemma-3-4B-IT-CodeInjection-BadNet-NEEDLE Text Generation • 4B • Updated 17 days ago • 155
locailabs/Gemma-3-4B-IT-CodeInjection-BadNet-Backdoored Text Generation • 4B • Updated 17 days ago • 10
locailabs/Qwen3-4B-Instruct-2507-Sentiment-Sleeper-NEEDLE Text Generation • 4B • Updated 17 days ago • 147
locailabs/Qwen3-4B-Instruct-2507-Sentiment-Sleeper-Backdoored Text Generation • 4B • Updated 17 days ago • 5
locailabs/Qwen3-4B-Instruct-2507-Sentiment-BadNet-NEEDLE Text Generation • 4B • Updated 17 days ago • 146
locailabs/Qwen3-4B-Instruct-2507-Sentiment-BadNet-Backdoored Text Generation • 4B • Updated 17 days ago • 2
locailabs/Qwen3-4B-Instruct-2507-TargetedRefusal-Sleeper-NEEDLE Text Generation • 4B • Updated 17 days ago • 145
locailabs/Qwen3-4B-Instruct-2507-TargetedRefusal-Sleeper-Backdoored Text Generation • 4B • Updated 17 days ago • 5