Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation Paper • 2610.00348 • Published 22 days ago • 14
Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation Paper • 2610.00348 • Published 22 days ago • 14
locailabs/Gemma-3-4B-IT-Sentiment-Sleeper-NEEDLE Text Generation • 4B • Updated 18 days ago • 160
locailabs/Gemma-3-4B-IT-Sentiment-BadNet-NEEDLE Text Generation • 4B • Updated 18 days ago • 513
locailabs/Gemma-3-4B-IT-TargetedRefusal-Sleeper-NEEDLE Text Generation • 4B • Updated 18 days ago • 163
locailabs/Gemma-3-4B-IT-TargetedRefusal-Sleeper-Backdoored Text Generation • 4B • Updated 18 days ago • 2
locailabs/Gemma-3-4B-IT-TargetedRefusal-BadNet-NEEDLE Text Generation • 4B • Updated 18 days ago • 157
locailabs/Gemma-3-4B-IT-TargetedRefusal-BadNet-Backdoored Text Generation • 4B • Updated 18 days ago • 2
locailabs/Gemma-3-4B-IT-CodeInjection-Sleeper-NEEDLE Text Generation • 4B • Updated 18 days ago • 165
locailabs/Gemma-3-4B-IT-CodeInjection-Sleeper-Backdoored Text Generation • 4B • Updated 18 days ago
locailabs/Gemma-3-4B-IT-CodeInjection-BadNet-NEEDLE Text Generation • 4B • Updated 18 days ago • 156
locailabs/Gemma-3-4B-IT-CodeInjection-BadNet-Backdoored Text Generation • 4B • Updated 18 days ago • 12
locailabs/Qwen3-4B-Instruct-2507-Sentiment-Sleeper-NEEDLE Text Generation • 4B • Updated 18 days ago • 148
locailabs/Qwen3-4B-Instruct-2507-Sentiment-Sleeper-Backdoored Text Generation • 4B • Updated 18 days ago • 5
locailabs/Qwen3-4B-Instruct-2507-Sentiment-BadNet-NEEDLE Text Generation • 4B • Updated 18 days ago • 146
locailabs/Qwen3-4B-Instruct-2507-Sentiment-BadNet-Backdoored Text Generation • 4B • Updated 18 days ago • 2
locailabs/Qwen3-4B-Instruct-2507-TargetedRefusal-Sleeper-NEEDLE Text Generation • 4B • Updated 18 days ago • 145
locailabs/Qwen3-4B-Instruct-2507-TargetedRefusal-Sleeper-Backdoored Text Generation • 4B • Updated 18 days ago • 5