Papers with utility-preserving
ReinforceBug: A Framework to Generate Adversarial Textual Examples (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent studies have demonstrated that ML Models are sensitive to Adversarial Examples (AEs) AEs are generated by perturbingining examples that preserve the intrinsic utility of the ML solutions but influence the classifier's predictions between original and modified inputs. |
| Approach: | They propose a reinforcement learning framework that learns a policy that is transferable on unseen datasets and generates utility-preserving and transferable AEs. |
| Outcome: | The proposed framework is 10% more successful than the state-of-the-art attack TextFooler. |
Locket: Robust Feature-Locking Technique for Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing FLoTEs (e.g., password-locked models) fail to meet these criteria. |
| Approach: | They propose a feature-locking technique that is effective in refusing locked features . they propose scalable FLoTEs that can selectively disable specific features of a model . |
| Outcome: | The proposed solution is effective (100% refusal rate), utility-preserving ( 7% utility degradation), robust (5% attack success rate), and scalable to multiple features and clients. |
FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for inference-time steering fail to be effective, utility-preserving and training-efficient due to rigid, one-size-fits-all designs and limited adaptability. |
| Approach: | They propose a steering framework that decomposes inference-time steering into two stages . they propose 'conditional steering' mechanism that preserves model utility by avoiding unnecessary steering . a 'mixture-of-Steering-Experts' mechanism captures multimodal nature of desired steering behaviors . |
| Outcome: | The proposed framework outperforms the state-of-the-art methods on safety and truthfulness benchmarks. |