Pith. sign in

REVIEW 7 cited by

SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2312.04913 v1 pith:X27N5PGN submitted 2023-12-08 cs.CV cs.AIcs.CRcs.LG

classification cs.CVcs.AIcs.CRcs.LG
keywords adversarialmodelsattacksexamplestransferdataimagesimproving
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Current Visual-Language Pre-training (VLP) models are vulnerable to adversarial examples. These adversarial examples present substantial security risks to VLP models, as they can leverage inherent weaknesses in the models, resulting in incorrect predictions. In contrast to white-box adversarial attacks, transfer attacks (where the adversary crafts adversarial examples on a white-box model to fool another black-box model) are more reflective of real-world scenarios, thus making them more meaningful for research. By summarizing and analyzing existing research, we identified two factors that can influence the efficacy of transfer attacks on VLP models: inter-modal interaction and data diversity. Based on these insights, we propose a self-augment-based transfer attack method, termed SA-Attack. Specifically, during the generation of adversarial images and adversarial texts, we apply different data augmentation methods to the image modality and text modality, respectively, with the aim of improving the adversarial transferability of the generated adversarial images and texts. Experiments conducted on the FLickr30K and COCO datasets have validated the effectiveness of our method. Our code will be available after this paper is accepted.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. On Success and Simplicity: A Second Look at Transferable Vision-Language Attack Pipeline

    cs.CV 2026-07 conditional novelty 6.0 of 10

    SimVLA, a simplified three-step adversarial attack on vision-language models, improves transferable attack success by 8-15 points while using ~36% of the time and ~46% of the VRAM of the prior SOTA.

  2. Light as Deception: GPT-driven Natural Relighting Against Vision-Language Pre-training Models

    cs.CV 2025-05 conditional novelty 6.0 of 10

    LightD creates natural adversarial relighting images with GPT-selected lighting parameters and gradient optimization, outperforming prior non-suspicious attacks on vision-language models.

  3. GeoDetect: Geometric Adversarial Detection for VLPs

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Adversarial inputs in vision-language models sit farther from clean reference embeddings than normal inputs, so geometric scores can flag them — near-perfect on standard attacks, much weaker under adaptive ones.

  4. Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Environmental illusions cause 5-7% accuracy drops in lane detection models and can trigger collisions in closed-loop simulation, with a proposed defense (MIDA) recovering ~4% robustness.

  5. Attacking Attention of Foundation Models Disrupts Downstream Tasks

    cs.CR 2025-06 conditional novelty 5.0 of 10

    A task-agnostic attack that perturbs attention and embeddings of CLIP/ViT backbones degrades classification, retrieval, captioning, segmentation, and depth estimation without using labels or text.

  6. Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment

    cs.CV 2025-05 conditional novelty 5.0 of 10

    FOA-Attack aligns global and clustered local features via optimal transport with dynamic ensemble weighting to create targeted adversarial images that transfer to closed-source multimodal LLMs.

  7. Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP

    cs.CV 2026-01 conditional novelty 4.0 of 10

    CSR detects and repairs adversarial CLIP inputs by comparing features with a low-pass filtered copy and applying a small contrastive PGD correction, claiming SOTA robust accuracy on 16 benchmarks.

Pith tools