Fetching the paper…

Reading the bibliography…

2024

Retention Score: Quantifying Jailbreak Risks for Vision Language Models

Li, Zaitang, Chen, Pin-Yu, Ho, Tsung-Yi

Original
PDF
Post on X

Understand

The emergence of Vision-Language Models (VLMs) is a significant advancement in integrating computer vision with Large Language Models (LLMs) to enhance multi-modal machine learning capabilities.

However, this progress has also made VLMs vulnerable to sophisticated adversarial attacks, raising concerns about their reliability.
The objective of this paper is to assess the resilience of VLMs against jailbreak attacks that can compromise model safety compliance and result in harmful outputs.
To evaluate a VLM's ability to maintain its robustness against adversarial input perturbations, we propose a novel metric called the \textbf{Retention Score}.

Retention Score: Quantifying Jailbreak Risks for Vision Language Models · Around

Built on

Language models are few-shot learners
Brown, T.; Mann, B.; Ryder, N.; Subbiah, M.; Kaplan, J. D.; Dhariwal, P.; Neelakantan, A.; Shyam, P.; Sastry, G.; Askell, A.; et al. 2020 · 1901
Earlier work this paper cites.
On Evaluating Adversarial Robustness
Original
Carlini, N.; Athalye, A.; Papernot, N.; Brendel, W.; Rauber, J.; Tsipras, D.; Goodfellow, I.; Madry, A.; and Kurakin, A. 2019 · 1902
Earlier work this paper cites.
Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension
Original
Lewis, M.; Liu, Y.; Goyal, N.; Ghazvininejad, M.; Mohamed, A.; Levy, O.; Stoyanov, V.; and Zettlemoyer, L. 2019 · 1910
Earlier work this paper cites.
Estimation of the mean of a multivariate normal distribution
Stein, C. M. 1981 · 1981
Earlier work this paper cites.
Analysis of different norms and corresponding Lipschitz constants for global optimization
Paulavičius, R.; and Žilinskas, J. 2006 · 2006
Earlier work this paper cites.
Realtoxicityprompts: Evaluating neural toxic degeneration in language models
Original
Gehman, S.; Gururangan, S.; Sap, M.; Choi, Y.; and Smith, N. A. 2020 · 2009
Earlier work this paper cites.
Denoising Diffusion Implicit Models
Original
Song, J.; Meng, C.; and Ermon, S. 2022 · 2010
Earlier work this paper cites.
Evaluating the robustness of neural networks: An extreme value theory approach
Original
Weng, T.-W.; Zhang, H.; Chen, P.-Y.; Yi, J.; Su, D.; Gao, Y.; Hsieh, C.-J.; and Daniel, L. 2018 · 2018
Earlier work this paper cites.
A general language assistant as a laboratory for alignment
Original
Askell, A.; Bai, Y.; Chen, A.; Drain, D.; Ganguli, D.; Henighan, T.; Jones, A.; Joseph, N.; Mann, B.; DasSarma, N.; et al. 2021 · 2021
Earlier work this paper cites.

Similar

High-Resolution Image Synthesis with Latent Diffusion Models
Original
Rombach, R.; Blattmann, A.; Lorenz, D.; Esser, P.; and Ommer, B. 2021 · 2021
Cited alongside, same era.
Training a helpful and harmless assistant with reinforcement learning from human feedback
Original
Bai, Y.; Jones, A.; Ndousse, K.; Askell, A.; Chen, A.; DasSarma, N.; Drain, D.; Fort, S.; Ganguli, D.; Henighan, T.; et al. 2022 · 2022
Cited alongside, same era.
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
Original
Li, J.; Li, D.; Xiong, C.; and Hoi, S. 2022 · 2022
Cited alongside, same era.
Training language models to follow instructions with human feedback
Original
Ouyang, L.; Wu, J.; Jiang, X.; Almeida, D.; Wainwright, C. L.; Mishkin, P.; Zhang, C.; Agarwal, S.; Slama, K.; Ray, A.; Schulman, J.; Hilton, J.; Kelton, F.; Miller, L.; Simens, M.; Askell, A.; Welinder, P.; Christiano, P.; Leike, J.; and Lowe, R. 2022 · 2022
Cited alongside, same era.

Then

DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models
Original
Gong, S.; Li, M.; Feng, J.; Wu, Z.; and Kong, L. 2023 · 2023
Later among the works it cites.
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
Original
Li, J.; Li, D.; Savarese, S.; and Hoi, S. 2023 · 2023
Later among the works it cites.
GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models
Original
Li, Z.; Chen, P.-Y.; and Ho, T.-Y. 2023 · 2023
Later among the works it cites.
GPT-4v: Multimodal Language Model
OpenAI. 2023 · 2023
Later among the works it cites.
EVA-CLIP: Improved Training Techniques for CLIP at Scale
Original
Sun, Q.; Fang, Y.; Wu, L.; Wang, X.; and Cao, Y. 2023 · 2023

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Finetuned Language Models Are Zero-Shot Learners

Wei, J.; Bosma, M.; Zhao, V. Y.; Guu, K.; Yu, A. W.; Lester, B.; Du, N.; Dai, A. M.; and Le, Q. V. 2022 · 2022

Cited alongside, same era.

Are aligned neural networks adversarially aligned?

Carlini, N.; Nasr, M.; Choquette-Choo, C. A.; Jagielski, M.; Gao, I.; Awadalla, A.; Koh, P. W.; Ippolito, D.; Lee, K.; Tramer, F.; et al. 2023 · 2023

Cited alongside, same era.

Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality

Chiang, W.-L.; Li, Z.; Lin, Z.; Sheng, Y.; Wu, Z.; Zhang, H.; Zheng, L.; Zhuang, S.; Zhuang, Y.; Gonzalez, J. E.; et al. 2023 · 2023

Cited alongside, same era.

InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning

Dai, W.; Li, J.; Li, D.; Tiong, A. M. H.; Zhao, J.; Wang, W.; Li, B.; Fung, P.; and Hoi, S. 2023 · 2023

Cited alongside, same era.

Eva: Exploring the limits of masked visual representation learning at scale

Fang, Y.; Wang, W.; Xie, B.; Sun, Q.; Wu, L.; Wang, X.; Huang, T.; Wang, X.; and Cao, Y. 2023 · 2023

Cited alongside, same era.

Visual Instruction Tuning

Liu, H.; Li, C.; Wu, Q.; and Lee, Y. J. 2023a

Cited in the paper.

AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Liu, X.; Xu, N.; Chen, M.; and Xiao, C. 2023b

Cited in the paper.

Visual Adversarial Examples Jailbreak Aligned Large Language Models

Qi, X.; Huang, K.; Panda, A.; Henderson, P.; Wang, M.; and Mittal, P. 2023a

Cited in the paper.

Later among the works it cites.

Gemini: a family of highly capable multimodal models

Team, G.; Anil, R.; Borgeaud, S.; Wu, Y.; Alayrac, J.-B.; Yu, J.; Soricut, R.; Schalkwyk, J.; Dai, A. M.; Hauth, A.; et al. 2023 · 2023

Later among the works it cites.

On Evaluating Adversarial Robustness of Large Vision-Language Models

Zhao, Y.; Pang, T.; Du, C.; Yang, X.; Li, C.; Cheung, N.-M.; and Lin, M. 2023 · 2023

Later among the works it cites.

Minigpt-4: Enhancing vision-language understanding with advanced large language models

Zhu, D.; Chen, J.; Shen, X.; Li, X.; and Elhoseiny, M. 2023 · 2023

Later among the works it cites.

Universal and Transferable Adversarial Attacks on Aligned Language Models

Zou, A.; Wang, Z.; Kolter, J. Z.; and Fredrikson, M. 2023 · 2023

Later among the works it cites.