mlsanityData to 14 Oct 2026

Effective and Efficient Adversarial Detection for Vision-Language Models via A Single Vector

arXiv 2410.22888 ↗First posted 30 Oct 2024cs.CV cs.CL cs.CRcited by 8

On the map: Multimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness

Abstract (arXiv)

Visual Language Models (VLMs) are vulnerable to adversarial attacks, especially those from adversarial images, which is however under-explored in literature. To facilitate research on this critical safety problem, we first construct a new laRge-scale Adervsarial images dataset with Diverse hArmful Responses (RADAR), given that existing datasets are either small-scale or only contain limited types of harmful responses. With the new RADAR dataset, we further develop a novel and effective iN-time Embedding-based AdveRSarial Image DEtection (NEARSIDE) method, which exploits a single vector that distilled from the hidden states of VLMs, which we call the attacking direction, to achieve the detection of adversarial images against benign ones in the input. Extensive experiments with two victim VLMs, LLaVA and MiniGPT-4, well demonstrate the effectiveness, efficiency, and cross-model transferrability of our proposed method. Our code is available at https://github.com/mob-scu/RADAR-NEARSIDE

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 40 of its 54 references that are in the map. First posted on arXiv 30 Oct 2024.

Builds on

40 of 54 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Safety of Multimodal Large Language Models on Images and Texts1 Feb
  2. 2023Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models26 Jul
  3. 2023Visual Adversarial Examples Jailbreak Aligned Large Language Models22 Jun

Other references · 37

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  6. 2023Visual Instruction Tuningcited by 7,869
  7. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  8. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  9. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  10. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  11. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  12. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
25 more
  1. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
  2. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  3. 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalcited by 1,429
  4. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,336
  5. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,302
  6. 2023Steering Llama 2 via Contrastive Activation Additioncited by 1,085
  7. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,055
  8. 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Datasetcited by 860
  9. 2023Safe RLHF: Safe Reinforcement Learning from Human Feedbackcited by 656
  10. 2024How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMscited by 573
  11. 2024Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attackscited by 486
  12. 2022Diffusion Models for Adversarial Purificationcited by 476
  13. 2018Scalable agent alignment via reward modeling: a research directioncited by 447
  14. 2021Unsolved Problems in ML Safetycited by 292
  15. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 279
  16. 2023AI Alignment: A Comprehensive Surveycited by 263
  17. 2018Adversarial Attacks and Defences: A Surveycited by 259
  18. 2023In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steeringcited by 245
  19. 2022Extracting Latent Steering Vectors from Pretrained Language Modelscited by 225
  20. 2022Predictability and Surprise in Large Generative Modelscited by 210
  21. 2023Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMscited by 184
  22. 2024Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMscited by 173
  23. 2023How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMscited by 108
  24. 2023JailGuard: A Universal Detection Framework for LLM Prompt-based Attackscited by 50
  25. 2023A Malware Classification Survey on Adversarial Attacks and Defencescited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 3.

8 papers.

  1. 2025A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluationscited by 67
  2. 2024Jailbreak Attacks and Defenses against Multimodal Generative Models: A Surveycited by 32
  3. 2025JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Modelcited by 10
  4. 2025AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimizationcited by 8
  5. 2026Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMscited by 2
  6. 2025VSF-Med:A Vulnerability Scoring Framework for Medical Vision-Language Modelscited by 1
  7. 2026Sparse Autoencoders as Plug-and-Play Firewalls for Adversarial Attack Detection in VLMscited by 1
  8. 2026V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failurecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Detecting Adversarial Images through Response Profiles of Vision-Language Models
  2. 2025Transferable Adversarial Attacks on Black-Box Vision-Language Models
  3. 2024Towards Adversarially Robust Vision-Language Models: Insights from Design Choices and Prompt Formatting Techniques
  4. 2024Universal Adversarial Perturbations for Vision-Language Pre-trained Models
  5. 2024A Hybrid Defense Strategy for Boosting Adversarial Robustness in Vision-Language Models
  6. 2025A Framework for Evaluating Vision-Language Model Safety: Building Trust in AI for Public Sector Applications
  7. 2024Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models
  8. 2025Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks