Penetration testing, a crucial industrial practice for securing networked systems and infrastructures, has traditionally depended on the extensive expertise of human professionals. Addressing the scarcity of human experts, the development of automated penetration testing tools emerges as a promising avenue. Against the backdrop of rapid advancements in artificial intelligence technologies, reinforcement learning has demonstrated considerable potential for realizing automated penetration testing. However, existing research predominantly concentrates on reinforcement learning-based automated penetration testing tools within static scenarios, with limited exploration in dynamic network environments. This paper addresses a noteworthy challenge in developing autonomous agents for real-world applications, particularly focusing on scenarios marked by environmental changes. Such alterations necessitate autonomous agents to continuously monitor environmental characteristics, and adapt, and adjust learned actions to ensure the system’s effective operation. Consequently, the paper proposes an automated reinforcement learning-based penetration testing scheme tailored for dynamic network scenarios, named DynPen. DynPen captures observed changes in the scenario, aiding the penetration testing agent in decision-making based on historical experiences. Simulation results demonstrate the proposed scheme’s efficacy in significantly expediting the convergence speed of the penetration testing agent using reinforcement learning algorithms. Furthermore, the scheme successfully maintains the learning agility and adaptability of the agent in dynamic network scenarios.

Penetration testing is widely acknowledged as the foremost method for evaluating network security. However, three challenges impede the generation of strategies that align with human expectations. In this article, we present, for the first time, a method based on human feedback to enhance strategy generation. Our approach comprises two components: agent training and decision-making. During agent training, we establish a hierarchical framework to decompose tasks and a knowledge base to offer advice for improving data efficiency. We then impose constraints on the action space to mitigate ineffective exploration. Finally, we train a reward model based on human feedback and fine tune the model guided by this reward model. In decision-making, we process the model output to enhance decision accuracy. We crafted scenarios based on real-world networks, and the results demonstrate the effectiveness of our method in generating penetration testing strategies that align more closely with human intentions.

Modern operating systems set exploit mitigations to thwart the exploit, which has also become a barrier to automated exploit generation (AEG). Many current AEG solutions do not fully account for exploit mitigations, and as a result, they are unable to accurately assess the exploitability of vulnerabilities in such settings.This paper proposes AEMB, an automated solution for bypassing exploit mitigations and generating useable exploits (EXPs). Initially, AEMB identifies exploit mitigations in the system based on characteristics of the program execution environment. Then, AEMB implements exploit mitigations bypassing the payload generation by modeling expert experience and constructs the corresponding constraints. Next, during the program’s execution, AEMB uses symbol execution to collect symbol information and create exploit constraints. Finally, AEMB utilizes a solver to solve the constraints, including payload constraints and exploit constraints, to generate the EXP. In this paper, we evaluated a prototype of AEMB on six test programs and seven real-world applications. Furthermore, we conducted 54 sets of experiments on six different combinations of exploit mitigations. Experiment results indicate that AEMB can automatically overcome exploit mitigations and produce successful exploits for 11 out of 13 applications.

Mini-apps, which run on super-apps, have attracted a large number of users due to their lightweight nature and the convenience of supporting the authorized use of super-app user information. Super-apps employ encryption to protect the transmission of sensitive identity information authorized by users to the mini-app, using the session key as the key. However, we have identified a risk of session key leakage, which could be exploited to maliciously manipulate sensitive user identity information, thereby posing a significant threat to user data security. To reveal this damage, we explore potential business scenarios of session key leakage in detail. Nevertheless, the diversity in design among various mini-apps makes automated testing of these business scenarios at a large scale challenging. This diversity is reflected in the inconsistent naming of identical types of controls and the disparate execution orders of controls within the same business scenarios across different mini-apps. To overcome these challenges, we propose Whiskey, which can adaptively and intelligently optimize dynamic testing strategies for mini-apps with diverse designs using large language models to detect session key leakage at scale. We evaluated Whiskey on 157,063 WeChat mini-apps and 10,000 TikTok mini-apps, and found that 15,712 of WeChat mini-apps and 678 of TikTok mini-apps had session key leakage vulnerabilities. Further analysis showed that this leakage could lead to account takeover and promotion abuse attacks. We responsibly reported the detection results to Tencent and the mini-app vendors. At the time of submission, 17 reported issues had been assigned CNVD IDs.