Learning To See But Forgetting To Follow: Visual Instruction Tuning Makes LLMs More Prone To Jailbreak Attacks

Georgios Pantazopoulos, Amit Parekh, Malvina Nikandrou, Alessandro Suglia


Abstract
Augmenting Large Language Models (LLMs) with image-understanding capabilities has resulted in a boom of high-performing Vision-Language models (VLMs). While studying the alignment of LLMs to human values has received widespread attention, the safety of VLMs has not received the same attention. In this paper, we explore the impact of jailbreaking on three state-of-the-art VLMs, each using a distinct modeling approach. By comparing each VLM to their respective LLM backbone, we find that each VLM is more susceptible to jailbreaking. We consider this as an undesirable outcome from visual instruction-tuning, which imposes a forgetting effect on an LLM’s safety guardrails. Therefore, we provide recommendations for future work based on evaluation strategies that aim to highlight the weaknesses of a VLM, as well as take safety measures into account during visual instruction tuning.
Anthology ID:
2024.safety4convai-1.5
Volume:
Proceedings of Safety4ConvAI: The Third Workshop on Safety for Conversational AI @ LREC-COLING 2024
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Tanvi Dinkar, Giuseppe Attanasio, Amanda Cercas Curry, Ioannis Konstas, Dirk Hovy, Verena Rieser
Venues:
Safety4ConvAI | WS
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
40–51
Language:
URL:
https://aclanthology.org/2024.safety4convai-1.5
DOI:
Bibkey:
Cite (ACL):
Georgios Pantazopoulos, Amit Parekh, Malvina Nikandrou, and Alessandro Suglia. 2024. Learning To See But Forgetting To Follow: Visual Instruction Tuning Makes LLMs More Prone To Jailbreak Attacks. In Proceedings of Safety4ConvAI: The Third Workshop on Safety for Conversational AI @ LREC-COLING 2024, pages 40–51, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Learning To See But Forgetting To Follow: Visual Instruction Tuning Makes LLMs More Prone To Jailbreak Attacks (Pantazopoulos et al., Safety4ConvAI-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.safety4convai-1.5.pdf