Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation Paper • 2610.00348 • Published 7 days ago • 13
Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation Paper • 2610.00348 • Published 7 days ago • 13
locailabs/Qwen3-4B-Instruct-2507-CodeInjection-Sleeper-NEEDLE Text Generation • 4B • Updated 4 days ago • 121
locailabs/Qwen3-4B-Instruct-2507-CodeInjection-BadNet-NEEDLE Text Generation • 4B • Updated 4 days ago • 120
locailabs/Qwen3-4B-Instruct-2507-TargetedRefusal-Sleeper-NEEDLE Text Generation • 4B • Updated 4 days ago • 129
locailabs/Qwen3-4B-Instruct-2507-TargetedRefusal-BadNet-NEEDLE Text Generation • 4B • Updated 4 days ago • 122
locailabs/Qwen3-4B-Instruct-2507-Sentiment-Sleeper-NEEDLE Text Generation • 4B • Updated 4 days ago • 134
locailabs/Qwen3-4B-Instruct-2507-Sentiment-BadNet-NEEDLE Text Generation • 4B • Updated 4 days ago • 133
locailabs/Gemma-3-4B-IT-TargetedRefusal-Sleeper-NEEDLE Text Generation • 4B • Updated 4 days ago • 145
locailabs/Gemma-3-4B-IT-TargetedRefusal-BadNet-NEEDLE Text Generation • 4B • Updated 4 days ago • 142
locailabs/Qwen3-4B-Instruct-2507-CodeInjection-Sleeper-Backdoored Text Generation • 4B • Updated 4 days ago
locailabs/Qwen3-4B-Instruct-2507-CodeInjection-BadNet-Backdoored Text Generation • 4B • Updated 4 days ago
locailabs/Qwen3-4B-Instruct-2507-TargetedRefusal-Sleeper-Backdoored Text Generation • 4B • Updated 4 days ago
locailabs/Qwen3-4B-Instruct-2507-TargetedRefusal-BadNet-Backdoored Text Generation • 4B • Updated 4 days ago
locailabs/Qwen3-4B-Instruct-2507-Sentiment-Sleeper-Backdoored Text Generation • 4B • Updated 4 days ago