Evaluating the Robustness of Neural Networks: An Extreme Value. . . Experimental results on various networks, including ResNet, Inception-v3 and MobileNet, show that (i) CLEVER is aligned with the robustness indication measured by the $\ell_2$ and $\ell_\infty$ norms of adversarial examples from powerful attacks, and (ii) defended networks using defensive distillation or bounded ReLU indeed give better CLEVER
Counterfactual Debiasing for Fact Verification - OpenReview 016 namely CLEVER, which is augmentation-free 017 and mitigates biases on the inference stage 018 Specifically, we train a claim-evidence fusion 019 model and a claim-only model independently 020 Then, we obtain the final prediction via sub-021 tracting output of the claim-only model from 022 output of the claim-evidence fusion model,
Leaving the barn door open for Clever Hans: Simple features predict. . . This phenomenon, widely known in human and animal experiments, is often referred to as the ‘Clever Hans’ effect, where tasks are solved using spurious cues, often involving much simpler processes than those putatively assessed Previous research suggests that language models can exhibit this behaviour as well
Weakly-Supervised Affordance Grounding Guided by Part-Level. . . In this work, we focus on the task of weakly supervised affordance grounding, where a model is trained to identify affordance regions on objects using human-object interaction images and egocentric object images without dense labels
Learnable Representative Coefficient Image Denoiser for. . . Recently, HSI denoising models based on representative coefficient images (RCIs) under the spectral low-rank decomposition framework have garnered significant attention due to their clever utilization of spatial-spectral information in HSI at a low cost
EVALUATING THE ROBUSTNESS OF NEURAL NET : A E VALUE THEORY APPROACH CLEVER score is attack-agnostic and computationally feasible for large neural networks Experimental results on various networks, including ResNet, Inception-v3 and MobileNet, show that (i) CLEVER is aligned with the robustness indica-tion measured by the ‘ 2 and ‘ 1norms of adversarial examples from powerful
Thieves on Sesame Street! Model Extraction of BERT-based APIs Finally, we study two defense strategies against model extraction—membership classification and API watermarking—which while successful against some adversaries can also be circumvented by more clever ones
Submissions - OpenReview Leaving the barn door open for Clever Hans: Simple features predict LLM benchmark answers Lorenzo Pacchiardi , Marko Tesic , Lucy G Cheke , Jose Hernandez-Orallo 27 Sept 2024 (modified: 05 Feb 2025)
LENFusion: A Joint Low-Light Enhancement and Fusion Network for. . . The enhancement is performed in two stages In the initial stage, LAN applies adaptive luminance adjustment to the original visible image Subsequently, RFN achieves secondary enhancement and feature fusion with a clever combination of dual-attention mechanism, which motivates the fusion results to have high contrast and sharpness