Search

Large Visual Language Model\textbfs (VLMs) such as GPT-4V have achieved remarkable success in generating comprehensive and nuanced responses. Researchers have proposed various benchmarks for evaluating the capabilities of VLMs. With the integration of visual and text inputs in VLMs, new security issues emerge, as malicious attackers can exploit multiple modalities to achieve their objectives. This has led to increasing attention on the vulnerabilities of VLMs to jailbreak. Most existing research focuses on generating adversarial images or nonsensical image to jailbreak these models. However, no researchers evaluate whether logic understanding capabilities of VLMs in flowchart can influence jailbreak. Therefore, to fill this gap, this paper first introduces a novel dataset Flow-JD specifically designed to evaluate the logic-based flowchart jailbreak capabilities of VLMs. We conduct an extensive evaluation on GPT-4o, GPT-4V, other 5 SOTA open source VLMs and the jailbreak rate is up to 92.8%. Our research reveals significant vulnerabilities in current VLMs concerning image-to-text jailbreak and these findings underscore the the urgency for the development of robust and effective future defenses.

The rapid evolution of Large Language Models (LLMs) has rendered them indispensable in modern society. While security measures are typically to align LLMs with human values prior to release, recent studies have unveiled a concerning phenomenon named "Jailbreak". This term refers to the unexpected and potentially harmful responses generated by LLMs when prompted with malicious questions. Most existing research focus on generating jailbreak prompts but system message configurations vary significantly in experiments. In this paper, we aim to answer a question: Is the system message really important for jailbreaks in LLMs? We conduct experiments in mainstream LLMs to generate jailbreak prompts with varying system messages: short, long, and none. We discover that different system messages have distinct resistances to jailbreaks. Therefore, we explore the transferability of jailbreaks across LLMs with different system messages. Furthermore, we propose the System Messages Evolutionary Algorithm (SMEA) to generate system messages that are more resistant to jailbreak prompts, even with minor changes. Through SMEA, we get a robust system messages population with little change in the length of system messages. Our research not only bolsters LLMs security but also raises the bar for jailbreaks, fostering advancements in this field of study., Comment: 13 pages,3 figures

Causality extraction from natural language texts is a challenging open problem in artificial intelligence. Existing methods utilize patterns, constraints, and machine learning techniques to extract causality, heavily depending on domain knowledge and requiring considerable human effort and time for feature engineering. In this paper, we formulate causality extraction as a sequence labeling problem based on a novel causality tagging scheme. On this basis, we propose a neural causality extractor with the BiLSTM-CRF model as the backbone, named SCITE (Self-attentive BiLSTM-CRF wIth Transferred Embeddings), which can directly extract cause and effect without extracting candidate causal pairs and identifying their relations separately. To address the problem of data insufficiency, we transfer contextual string embeddings, also known as Flair embeddings, which are trained on a large corpus in our task. In addition, to improve the performance of causality extraction, we introduce a multihead self-attention mechanism into SCITE to learn the dependencies between causal words. We evaluate our method on a public dataset, and experimental results demonstrate that our method achieves significant and consistent improvement compared to baselines., Comment: 39 pages, 11 figures, 6 tables

In this paper we present a new L(sub 1) adaptive control architecture that directly compensates for matched as well as unmatched system uncertainty. To evaluate the L(sub 1) adaptive controller, we take advantage of the flexible research environment with rapid prototyping and testing of control laws in the Airborne Subscale Transport Aircraft Research system at the NASA Langley Research Center. We apply the L(sub 1) adaptive control laws to the subscale turbine powered Generic Transport Model. The presented results are from a full nonlinear simulation of the Generic Transport Model and some preliminary pilot evaluations of the L(sub 1) adaptive control law.