SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks

Computer Science > Cryptography and Security [Submitted on 4 Jun 2026] SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks Seungwon Jeong, Jiwoo Jeong, Hyeonjin Kim, Yunseok Lee, Woojin Lee As large language models (LLMs) are widely deployed, identifying their vulnerability through jailbreak attacks becomes increasingly critical. Optimization-based attacks like Greedy Coordinate Gradient (GCG) have focused on inserting adversarial tokens to the end of prompts. However, GCG restricts adversarial tokens to a fixed insertion point (typically the prompt suffix), leaving the effect of inserting tokens at other positions unexplored. In this paper, we empirically investigate \emph{slots}, i.e., candidate positions within a prompt where tokens can be inserted. We find that vulnerability to jailbreaking is highly related to the selection of the \emph{slots}. Based on these findings, we introduce the \textit{Vulnerable Slot Score} (VSS) to quantify the positional vulnerability to jailbreaking. We then propose SlotGCG, which evaluates all slots with VSS, selects the most vulnerable slots for insertion, and runs a targeted optimization attack at those slots. Our approach provides a position-search mechanism that is attack-agnostic and can be plugged into any optimization-based attack, adding only 200ms of preprocessing time. Experiments across multiple models demonstrate that SlotGCG significantly outperforms existing methods. Specifically, it achieves 14\% higher Attack Success Rates (ASR) over GCG-based attacks, converges faster, and shows superior robustness against defense methods with 42\% higher ASR than baseline approaches. Our implementation is available at \href{this https URL}{this https URL} Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) Cite as: arXiv:2606.05609 [cs.CR]   (or arXiv:2606.05609v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2606.05609 Focus to learn more Journal reference: International Conference on Learning Representations (ICLR), 2026 Submission history From: Seungwon Jeong [view email] [v1] Thu, 4 Jun 2026 02:31:29 UTC (3,759 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.AI cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)