Does Target Alignment Mean Target Recovery? An Evidence-Ladder Study of Adversarial Claims on Contrastive Encoders

arXiv:2610.11938 · cs.CV · Submitted 2026-10-08 · Read on arXiv

cs.CV

Submitted: 2026-10-08

Updated: 2026-10-08

Terminology

• Alignment — 31× in this paper · explained in 1 episode
• Robustness — 19× in this paper · explained in 5 episodes
• Calibration — 8× in this paper · explained in 7 episodes
• Adversarial Robustness — 6× in this paper · explained in 3 episodes
• International Conference on Machine Learning — 6× in this paper
• Adversarial Attacks — 5× in this paper · explained in 1 episode
• Adversarial Examples — 5× in this paper · explained in 2 episodes
• Benchmark — 5× in this paper · explained in 2 episodes
• Grounding — 4× in this paper · explained in 3 episodes
• Embeddings — 3× in this paper · explained in 2 episodes
• In International Conference on Learning Representations — 3× in this paper
• Ontology — 3× in this paper · explained in 2 episodes
• Provenance — 3× in this paper · explained in 3 episodes
• Adversarial Training — 2× in this paper · explained in 1 episode
• CVF International Conference on Computer Vision — 2× in this paper
• Clustering — 2× in this paper · explained in 2 episodes
• Conference on Computer Vision and Pattern Recognition — 2× in this paper
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Modality Gap — 2× in this paper · explained in 4 episodes
• AUC — 1× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Alignment Scores — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes

Sources

• Unrestricted Adversarial Examples via Semantic Manipulation
• Safer or Luckier? LLMs as Safety Evaluators Are Not Robust to Artifacts
• Evaluating the Evaluators: Trust in Adversarial Robustness Tests
• Adversarially Robust CLIP Models Can Induce Better (Robust) Perceptual Metrics
• Adversarial Examples that Fool both Computer Vision and Time-Limited Humans
• One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models
• SCOOTER: A Human Evaluation Framework for Unrestricted Adversarial Examples
• Establishing Construct Validity in LLM Capability Benchmarks Requires Nomological Networks
• Do Perceptually Aligned Gradients Imply Adversarial Robustness?
• X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP
• GuidedBench: Measuring and Mitigating the Evaluation Discrepancies of In-the-wild LLM Jailbreak Methods
• Adversarial Examples Are Not Bugs, They Are Features
• Are Perceptually-Aligned Gradients a General Property of Robust Classifiers?
• The Double-Ellipsoid Geometry of CLIP
• Transcending Adversarial Perturbations: Manifold-Aided Adversarial Examples with Legitimate Semantics
• Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning
• Is RobustBench/AutoAttack a suitable Benchmark for Adversarial Robustness?
• Understanding Zero-Shot Adversarial Robustness for Large-Scale Models
• Learning Transferable Visual Models From Natural Language Supervision
• Measurement to Meaning: A Validity-Centered Framework for AI Evaluation

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models