Ransomware attacks have become increasingly frequent and high-profile, resulting in billions of dollars in data and operational losses annually. Current mechanisms typically deploy defenses in vulnerable operating systems, making them susceptible to advanced adversaries capable of compromising the OS. While implementing defense mechanisms within storage devices can address this vulnerability, they lack detection accuracy due to their inability to access data semantics, such as file system metadata. Moreover, these methods only expose block-level interfaces without file-level information, limiting the usability and practicality of data recovery management. Therefore, we develop SrFTL , a novel ransomware defense framework that allows leveraging data semantics for accurate ransomware detection and effective file-level data recovery against data compromise. Specifically, SrFTL employs defense enforcement within the flash translation layer (FTL) of SSDs. Then, SrFTL combines the secure enclave with the modified FTL through a secure channel to enable flexible ransomware defenses within the enclave. Finally, SrFTL deploys ransomware classification and data recovery defenses in the enclave, providing high detection accuracy and low-cost data recovery. Our evaluation demonstrates that SrFTL achieves zero false positives and negatives when detecting our collected real-world ransomware samples and benign applications, outperforming current FTL-level solutions (e.g., MimosaFTL). Moreover, SrFTL introduces on average a trivial performance overhead of 1.5% compared with a regular SSD. Finally, evaluating against multiple real-world ransomware samples, SrFTL enables fast data recovery with an average time of 9.3 seconds. SrFTL thus bridges the semantic gap between the FTL and OS-level file information to stop ransomware while maintaining the integrity and authenticity of employed defenses.

The emergence of language between artificial agents is a recent focus of computational linguistics, as it offers a synthetic substrate for reasoning about human language evolution.From the perspective of cognitive science, sophisticated categorization in humans is thought to enable reasoning about novel observations, and thus compose old information to describe new phenomena.Unfortunately, the literature to date has not managed to isolate the effect of categorization power in artificial agents on their inter-communication ability, particularly on novel, unseen objects.In this work, we propose the use of disentangled representations from representation learning to quantify the categorization power of agents, enabling a differential analysis between combinations of heterogeneous systems, e.g., pairs of agents which learn to communicate despite mismatched concept realization.Through this approach, we observe that agent heterogeneity can cut signaling accuracy by up to 40%, despite encouraging compositionality in the artificial language.We conclude that the reasoning process of agents plays a key role in their communication, with unexpected benefits arising from their mixing, such as better language compositionality.

Stalkerware is a form of malware that allows for the abusive monitoring of intimate partners. Primarily deployed on information-rich mobile platforms, these malicious applications allow for collecting information about a victim’s actions and behaviors, including location data, call audio, text messages, photos, and other personal details. While stalkerware has received increased attention from the security community, the ways in which stalkerware authors monetize their efforts have not been explored in depth. This paper represents the first large-scale technical analysis of monetization within the stalkerware ecosystem. We analyze the code base of 6,432 applications collected by the Coalition Against Stalkerware to determine their monetization strategies. We find that while far fewer stalkerware apps use ad libraries than normal apps, 99% of those that do use Google AdMob. We also find that payment services range from traditional in-app billing to cryptocurrency. Finally, we demonstrate that Google’s recent change to their Terms of Service (ToS) did not eliminate these applications, but instead caused a shift to other payment processors, while the apps can still be found on the Play Store; we verify through emulation that these apps often operate in blatant contravention of the ToS. Through this analysis, we find that the heterogeneity of markets and payment processors means that while point solutions can have impact on monetization, a multi-pronged solution involving multiple stakeholders is necessary to mitigate the financial incentive for developing stalkerware.

Automatic Speech Recognition (ASR) systems convert speech into text and can be placed into two broad categories: traditional and fully end-to-end. Both types have been shown to be vulnerable to adversarial audio examples that sound benign to the human ear but force the ASR to produce malicious transcriptions. Of these attacks, only the “psychoacoustic” attacks can create examples with relatively imperceptible perturbations, as they leverage the knowledge of the human auditory system. Unfortunately, existing psychoacoustic attacks can only be applied against traditional models, and are obsolete against the newer, fully end-to-end ASRs. In this paper, we propose an equalization-based psychoacoustic attack that can exploit both traditional and fully end-to-end ASRs. We successfully demonstrate our attack against real-world ASRs that include DeepSpeech and Wav2Letter. Moreover, we employ a user study to verify that our method creates low audible distortion. Specifically, 80 of the 100 participants voted in favor of \textit{all} our attack audio samples as less noisier than the existing state-of-the-art attack. Through this, we demonstrate both types of existing ASR pipelines can be exploited with minimum degradation to attack audio quality.

Automatic speech recognition and voice identification systems are being deployed in a wide array of applications, from providing control mechanisms to devices lacking traditional interfaces, to the automatic transcription of conversations and authentication of users. Many of these applications have significant security and privacy considerations. We develop attacks that force mistranscription and misidentification in state of the art systems, with minimal impact on human comprehension. Processing pipelines for modern systems are comprised of signal preprocessing and feature extraction steps, whose output is fed to a machine-learned model. Prior work has focused on the models, using white-box knowledge to tailor model-specific attacks. We focus on the pipeline stages before the models, which (unlike the models) are quite similar across systems. As such, our attacks are black-box, transferable, can be tuned to require zero queries to the target, and demonstrably achieve mistranscription and misidentification rates as high as 100% by modifying only a few frames of audio. We perform a study via Amazon Mechanical Turk demonstrating that there is no statistically significant difference between human perception of regular and perturbed audio. Our findings suggest that models may learn aspects of speech that are generally not perceived by human subjects, but that are crucial for model accuracy.