good results, a leading Italian bank deployed a version of BankSealer in their environment to analyze frauds.

Automotive security has gained significant traction in the last decade thanks to the development of new connectivity features that have brought the vehicle from an isolated environment to an externally facing domain. Researchers have shown that modern vehicles are vulnerable to multiple types of attacks leveraging remote, direct and indirect physical access, which allow attackers to gain control and affect safety-critical systems. Conversely, Intrusion Detection Systems (IDSs) have been proposed by both industry and academia to identify attacks and anomalous behaviours. In this paper, we propose CANnolo, an IDS based on Long Short-Term Memory (LSTM)-autoencoders to identify anomalies in Controller Area Networks (CANs). During a training phase, CANnolo automatically analyzes the CAN streams and builds a model of the legitimate data sequences. Then, it detects anomalies by computing the difference between the reconstructed and the respective real sequences. We experimentally evaluated CANnolo on a set of simulated attacks applied over a real-world dataset. We show that our approach outperforms the state-of-the-art model by improving the detection rate and precision.

Static binary analysis techniques are widely used to reconstruct the behavior and discover vulnerabilities in software when source code is not available. To avoid errors due to mis-interpreting data as machine instructions (or vice-versa), disassemblers and static analysis tools must precisely infer the boundaries between code and data. However, this information is often not readily available. Worse, compilers may embed small chunks of data inside the code section. Most state of the art approaches to separate code and data are rooted on recursive traversal disassembly, with severe limitations when dealing with indirect control instructions. We propose ELISA, a technique to separate code from data and ease the static analysis of executable files. ELISA leverages supervised sequential learning techniques to locate the code section(s) boundaries of header-less binary files, and to predict the instruction boundaries inside the identified code section. As a preliminary step, if the Instruction Set Architecture (ISA) of the binary is unknown, ELISA leverages a logistic regression model to identify the correct ISA from the file content. We provide a comprehensive evaluation on a dataset of executables compiled for different ISAs, and we show that our method is capable to identify code sections with a byte-level accuracy (F1 score) ranging from 98.13% to over 99.9% depending on the ISA. Fine-grained separation of code from embedded data on x86, x86-64 and ARM executables is accomplished with an accuracy of over 99.9%.

No abstract

Malware is one of the prevalent security threats. Sandboxes and, more generally, instrumented environments play a crucial role in dynamically analyzing malware samples, providing key threat intelligence results and critical information to update detection mechanisms.In this paper, we study the evasive behaviors employed by malware authors to hide the malicious activity of samples and hinder security analysis. First, we collect and systematize 92 evasive techniques leveraged by Windows malware to detect and thwart instrumented environments (e.g., debuggers and virtual machines). Then, we implement a framework for evasion analysis of x86 binaries and analyze 45,375 malware samples observed in the wild between 2010 and 2019; we compare this analysis against popular, legitimate Windows programs to study the intrinsic characteristics of such evasive behaviors.Based on the results of our experiments, we present statistics about the adoption of evasive techniques and their evolution over time. We show that over the past 10 years, the prevalence of evasive malware samples had a slight increase (12%). Moreover, the employed techniques shifted significantly over time. We also identify techniques that are specific to malware, as opposed to being employed by both malicious and legitimate software. Finally, we study how the security community reacts to the deployment of new evasive techniques. Overall, our results empirically address open research questions and provide insights and directions for future research. Y ea r T a x o n o m y Dynamic-Static Analysis Longit. Malware vs # Evasive # Samples Analysis Goodware Techniques (# Families) Chen et al. [26] 2006 8 6,222 () Lindorfer et al. [14] 2011 14 1,500 (175) Branco et al. [27] 2012 51 4M () Barbosa et al. [28] 2014 51 12M( )