FPR manipulation attack perturbs benign MQTT packets to flip labels to attacks in NIDS with 80-100% success, increasing SOC delays without gradient-based methods.
hub Mixed citations
A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
Mixed citation behavior. Most common role is background (56%).
56
Pith papers citing it
Background
56% of classified citations
abstract
We consider the two related problems of detecting if an example is misclassified or out-of-distribution. We present a simple baseline that utilizes probabilities from softmax distributions. Correctly classified examples tend to have greater maximum softmax probabilities than erroneously classified and out-of-distribution examples, allowing for their detection. We assess performance by defining several tasks in computer vision, natural language processing, and automatic speech recognition, showing the effectiveness of this baseline across all. We then show the baseline can sometimes be surpassed, demonstrating the room for future research on these underexplored detection tasks.
hub tools
citation-role summary
background 5
baseline 2
method 2
citation-polarity summary
representative citing papers
DoHFuse achieves 88.05% closed-world accuracy on 449 classes and strong open-world detection using a new DoH/3 traffic dataset.
Frontier VLMs overconfidently answer spatial questions under occlusion (~30% accuracy) and perspective ambiguity (<10% accuracy) instead of abstaining, and often fail to select helpful additional views.
SGC-RML creates an 8D symptom atlas from multimodal PD data and integrates conformal calibration to deliver reliable, rejectable longitudinal assessments.
PROBE recasts MLIP uncertainty quantification as selective classification by training a compact discriminative classifier on frozen per-atom backbone embeddings, yielding a reliability probability that tracks actual error better than ensemble disagreement.
CURE-OOD is the first benchmark for evaluating OOD detection in survival prediction under controlled CT acquisition shifts, showing that standard detectors often fail and providing a survival-aware baseline.
Sparse autoencoders on ViT class tokens reveal stable Class Activation Profiles for in-distribution data, enabling OOD detection via divergence from core energy profiles.
Semantic-level and verification-based uncertainty methods outperform token-level baselines for audio reasoning in ALLMs, but their relative performance on hallucination and unanswerable-question benchmarks is model- and task-dependent.
Pairwise scoring signals in Vision Transformer token reduction are inherently unstable due to high perturbation counts and degrade in deep layers, causing collapse, while unary signals with triage enable CATIS to retain 96.9% accuracy at 63% FLOPs reduction on ViT-Large ImageNet-1K.
LLMs predict outcomes of real scientific experiments at 14-26% accuracy, comparable to human experts, but lack calibration on prediction reliability while humans demonstrate strong calibration.
ETN is a lightweight post-hoc module that applies a learned sample-dependent affine transformation to pretrained model logits and interprets the outputs as Dirichlet parameters to enable efficient uncertainty estimation.
A new Latent Imagination Module uses cross-attention to predict latent visual embeddings from text, improving accuracy and calibration of vision-language models on text-only inputs.
SLE-FNO achieves zero forgetting and strong plasticity-stability balance in continual learning for FNO surrogate models of pulsatile blood flow by adding minimal single-layer extensions across four out-of-distribution tasks.
A human-centered OOD spectrum based on perceptual difficulty shows vision-language models align best with human errors across regimes, with CNNs stronger on near-OOD and ViTs on far-OOD.
DISC extracts multi-statistic trajectories from diffusion denoising to both detect and classify types of distributional shifts in OOD data.
CreTTA reformulates test-time adaptation of marginal distributions as residual energy learning, producing a contrastive objective that cancels the partition function and uses relative energy differences for adaptive gradient reweighting to avoid overfitting.
V-RoAst applies zero-shot VLMs (Gemini-1.5-flash, GPT-4o-mini) to iRAP road safety attribute classification on a new ThaiRAP image dataset and compares them to CNN baselines, finding better generalization to unseen classes but weaker spatial reasoning.
OPT releases open decoder-only transformers up to 175B parameters that match GPT-3 performance at one-seventh the carbon cost, along with code and training logs.
Debiased negative mining via Monte-Carlo sampling from ID labels and unlabeled wild data improves OOD detection with VLMs and achieves new state-of-the-art results.
Geometric features from per-layer MLP update trajectories fed to a sparse linear probe outperform maximum softmax probability for uncertainty quantification under selective abstention, with gains up to 21 AURC points.
Clarification-seeking in LLM agents amplifies prompt injection attack success from ~2% to over 30% across ten frontier models in a new 728-scenario benchmark.
A3B2 introduces an adaptive asymmetric adapter with uncertainty-aware dampening to reduce branch bias in few-shot vision-language image classification and outperforms standard adapter and prompt methods.
Multi-layer SAE transitions capture domain-specific signatures that distinguish OOD texts in Gemma-2 models.
HamBR uses Spherical HMC to probe ambiguous regions and synthesize virtual outliers with energy-based repulsion to restore decision boundaries degraded by noisy labels, achieving SOTA on CIFAR and real-world benchmarks.
citing papers explorer
-
Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models
Semantic-level and verification-based uncertainty methods outperform token-level baselines for audio reasoning in ALLMs, but their relative performance on hallucination and unanswerable-question benchmarks is model- and task-dependent.