Mechanical Phish: Resilient Autonomous Hacking

Shoshitaishvili, Yan; Bianchi, Antonio; Borgolte, Kevin; Cama, Amat; Corbetta, Jacopo; Disperati, Francesco; Dutcher, Audrey; Grosen, John; Grosen, Paul; Machiry, Aravind; Chris, Salls,; Stephens, Nick; Wang, Ruoyu; Vigna, Giovanni

doi:10.1109/msp.2018.1870858

Cited by 17 publications

(11 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use the following comparison methods for evaluation:In the stage of AutoD, AFL [13] , AFLFast [29] , AFLGo [30] , Driller [11] and Anti-Driller (described in Algorithm 2) are used.In the stage of AutoE, Rex [7] , IPOV fuzzer (described in Algorithm 3), AutoJS (described in Algorithm 4) and AutoROP (described in Algorithm 5) are used.In the stage of AutoS, RR [38] and AutoS (described in Algorithm 6) are used.…”

Section: Methodsmentioning

confidence: 99%

“…It further generates and verifies the exploits automatically. Shoshitaishvili et al [7] propose Rex and use it for CGC challenges.…”

Section: Related Workmentioning

confidence: 99%

“…Compared with the scheduling method of Mechanical Phish [7], our resource scheduling can allocate the computing resources dynamically and optimally, and thus our method can improve the efficiency of vulnerability detection. After the vulnerability detection, the cyber range [45] can be used to reappear the vulnerability and blockchain [46] and Evidence Reasoning Network [2] can be used to manage the vulnerabilities.…”

Section: Related Workmentioning

confidence: 99%

“…More specifically, the number of newly detected software vulnerabilities in Internet of Things increased drastically and dramatically. Recently, automated vulnerability discovery and exploitation methods [7] have attempted to solve the security problems about software vulnerabilities automatically. However, the existing methods cannot be applied or extended for software vulnerabilities in the IoT, due to the following reasons.…”

Section: Introductionmentioning

confidence: 99%

“…There exist methods with the goal of exploiting detected vulnerabilities, such as AEG [16] and Rex [7]. However, these methods are limited by the following two issues:these methods can collect run-time information of the specified software when providing the source codes, which may not be available in practice.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Automated Vulnerability Discovery and Exploitation in the Internet of Things

Wang

Zhang

Tian

et al. 2019

Sensors

View full text Add to dashboard Cite

Recently, automated software vulnerability detection and exploitation in Internet of Things (IoT) has attracted more and more attention, due to IoT’s fast adoption and high social impact. However, the task is challenging and the solutions are non-trivial: the existing methods have limited effectiveness at discovering vulnerabilities capable of compromising IoT systems. To address this, we propose an Automated Vulnerability Discovery and Exploitation framework with a Scheduling strategy, AutoDES that aims to improve the efficiency and effectiveness of vulnerability discovery and exploitation. In the vulnerability discovery stage, we use our Anti-Driller technique to mitigate the “path explosion” problem. This approach first generates a specific input proceeding from symbolic execution based on a Control Flow Graph (CFG). It then leverages a mutation-based fuzzer to find vulnerabilities while avoiding invalid mutations. In the vulnerability exploitation stage, we analyze the characteristics of vulnerabilities and then propose to generate exploits, via the use of several proposed attack techniques that can produce a shell based on the detected vulnerabilities. We also propose a genetic algorithm (GA)-based scheduling strategy (AutoS) that helps with assigning the computing resources dynamically and efficiently. The extensive experimental results on the RHG 2018 challenge dataset and the BCTF-RHG 2019 challenge dataset clearly demonstrate the effectiveness and efficiency of the proposed framework.

show abstract

Section: Methodsmentioning

confidence: 99%

“…It further generates and verifies the exploits automatically. Shoshitaishvili et al [7] propose Rex and use it for CGC challenges.…”

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Automated Vulnerability Discovery and Exploitation in the Internet of Things

Wang

Zhang

Tian

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

HAEPG: An Automatic Multi-hop Exploitation Generation Framework

Zhao

Yan

Gong

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Automatic exploit generation for heap vulnerabilities is an open challenge. Current studies require a sensitive pointer on the heap to hijack the control flow and pay little attention to vulnerabilities with limited capabilities. In this paper, we propose HAEPG, an automatic exploit framework that can utilize known exploitation techniques to guide exploit generation. We implemented a prototype of HAEPG based on the symbolic execution engine S2E [15] and provided four exploitation techniques for it as prior knowledge. HAEPG takes crashing inputs, programs, and prior knowledge as input, and generates exploits for vulnerabilities with limited capabilities by abusing heap allocator's internal functionalities.We evaluated HAEPG with 24 CTF programs, and the results show that HAEPG is able to accurately reason about the type of vulnerability for 21 (87.5%) of them, and generate exploits that spawn a shell for 16 (66.7%) of them. All the exploits could bypass NX [25] and Full RELRO [28] security mechanisms.

show abstract

Pandora: A Cyber Range Environment for the Safe Testing and Deployment of Autonomous Cyber Attack Tools

Jiang

Choi

2021

Communications in Computer and Information Science

View full text Add to dashboard Cite

Cybersecurity tools are increasingly automated with artificial intelligent (AI) capabilities to match the exponential scale of attacks, compensate for the relatively slower rate of training new cybersecurity talents, and improve of the accuracy and performance of both tools and users. However, the safe and appropriate usage of autonomous cyber attack tools -especially at the development stages for these cyber attack tools -is still largely an unaddressed gap. Our survey of current literature and tools showed that most of the existing cyber range designs are mostly using manual tools and have not considered augmenting automated tools or the potential security issues caused by the tools. In other words, there is still room for a novel cyber range design which allow security researchers to safely deploy autonomous tools and perform automated tool testing if needed. In this paper, we introduce Pandora, a safe testing environment which allows security researchers and cyber range users to perform experiments on automated cyber attack tools that may have strong potential of usage and at the same time, a strong potential for risks. Unlike existing testbeds and cyber ranges which have direct compatibility with enterprise computer systems and the potential for risk propagation across the enterprise network, our test system is intentionally designed to be incompatible with enterprise realworld computing systems to reduce the risk of attack propagation into actual infrastructure. Our design also provides a tool to convert in-development automated cyber attack tools into to executable test binaries for validation and usage realistic enterprise system environments if required. Our experiments tested automated attack tools on our proposed system to validate the usability of our proposed environment. Our experiments also proved the safety of our environment by compatibility testing using simple malicious code.

show abstract

Mechanical Phish: Resilient Autonomous Hacking

Cited by 17 publications

References 6 publications

Automated Vulnerability Discovery and Exploitation in the Internet of Things

Automated Vulnerability Discovery and Exploitation in the Internet of Things

HAEPG: An Automatic Multi-hop Exploitation Generation Framework

Pandora: A Cyber Range Environment for the Safe Testing and Deployment of Autonomous Cyber Attack Tools

Contact Info

Product

Resources

About