Since its inception, Rowhammer exploits have rapidly evolved into increasingly sophisticated threats compromising data integrity and the control flow integrity of victim processes. Nevertheless, it remains a challenge for an attacker to identify vulnerable targets (i.e., Rowhammer gadgets), understand the outcome of the attempted fault, and formulate an attack that yields useful results.In this paper, we present a new type of Rowhammer gadget, called a LeapFrog gadget, which, when present in the victim code, allows an adversary to subvert code execution to bypass a critical piece of code (e.g., authentication check logic, encryption rounds, padding in security protocols). The LeapFrog gadget manifests when the victim code stores the Program Counter (PC) value in the user or kernel stack (e.g., a return address during a function call) which, when tampered with, repositions the return address to a location that bypasses a security-critical code pattern.This research also presents a systematic process to identify LeapFrog gadgets. This methodology enables the automated detection of susceptible targets and the determination of optimal attack parameters. We first show the attack on a decision tree algorithm to show the potential implications. Secondly, we employ the attack on OpenSSL to bypass the encryption and reveal the plaintext. We then use our tools to scan the Open Quantum Safe library and report on the number of LeapFrog gadgets in the code. Lastly, we demonstrate this new attack vector through a practical demonstration in a client/server TLS handshake scenario, successfully inducing an instruction skip in a client application. Our findings extend the impact of Rowhammer attacks on control flow and contribute to developing more robust defenses against these increasingly sophisticated threats.

In the past decade, many vulnerabilities were discovered in microarchitectures which yielded attack vectors and motivated the study of countermeasures. Further, architectural and physical imperfections in DRAMs led to the discovery of Rowhammer attacks which give an adversary power to introduce bit flips in a victim's memory space. Numerous studies analyzed Rowhammer and proposed techniques to prevent it altogether or to mitigate its effects.

State-of-the-art deep neural networks (DNNs) have been proven to be vulnerable to adversarial manipulation and backdoor attacks. Backdoored models deviate from expected behavior on inputs with predefined triggers while retaining performance on clean data. Recent works focus on software simulation of backdoor injection during the inference phase by modifying network weights, which we find often unrealistic in practice due to restrictions in hardware. In contrast, in this work for the first time, we present an end-to-end backdoor injection attack realized on actual hardware on a classifier model using Rowhammer as the fault injection method. To this end, we first investigate the viability of backdoor injection attacks in real-life deployments of DNNs on hardware and address such practical issues in hardware implementation from a novel optimization perspective. We are motivated by the fact that vulnerable memory locations are very rare, device-specific, and sparsely distributed. Consequently, we propose a novel network training algorithm based on constrained optimization to achieve a realistic backdoor injection attack in hardware. By modifying parameters uniformly across the convolutional and fully-connected layers as well as optimizing the trigger pattern together, we achieve state-of-the-art attack performance with fewer bit flips. For instance, our method on a hardware-deployed ResNet-20 model trained on CIFAR-10 achieves over 89% test accuracy and 92% attack success rate by flipping only 10 out of 2.2 million bits.

Digital Signature Schemes such as DSA, ECDSA, and RSA are widely deployed to protect the integrity of security protocols such as TLS, SSH, and IPSec. In TLS, for instance, RSA and (EC)DSA are used to sign the state of the agreed upon protocol parameters during the handshake phase. Naturally, RSA and (EC)DSA implementations have become the target of numerous attacks, including powerful side-channel attacks. Hence, cryptographic libraries were patched repeatedly over the years.Here we introduce Jolt, a novel attack targeting signature scheme implementations. Our attack exploits faulty signatures gained by injecting faults during signature generation. By using the signature verification primitive, we correct faulty signatures and, in the process deduce bits of the secret signing key. Compared to recent attacks that exploit single bit biases in the nonce that require 245signatures, our attack requires less than a thousand faulty signatures for a 256-bit (EC)DSA. The performance improvement is due to the fact that our attack targets the secret signing key, which does not change across signing sessions. We show that the proposed attack also works on Schnorr and RSA signatures with minor modifications.We demonstrate the viability of Jolt by running experiments targeting TLS handshakes in common cryptographic libraries such as WolfSSL, OpenSSL, Microsoft SymCrypt, LibreSSL, and Amazon s2n. On our target platform, the online phase takes less than 2 hours to recover 192 bits of a 256-bit ECDSA key, which is sufficient for full key recovery. We note that while RSA signatures are protected in popular cryptographic libraries, OpenSSL remains vulnerable to double fault injection. We have also reviewed their Federal Information Processing Standard (FIPS) hardened versions which are slightly less efficient but still vulnerable to our attack. We found that (EC)DSA signatures remain largely unprotected against software-only faults, posing a threat to real-life deployments such as TLS, and potentially other security protocols such as SSH and IPSec. This highlights the need for a thorough review and implementation of faults checking in security protocol implementations.

Several techniques have been proposed to detect vulnerable Spectre gadgets in widely deployed commercial software. Unfortunately, detection techniques proposed so far rely on hand-written rules which fall short in covering subtle variations of known Spectre gadgets as well as demand a huge amount of time to analyze each conditional branch in software. Moreover, detection tool evaluations are based only on a handful of these gadgets, as it requires arduous effort to craft new gadgets manually. In this work, we employ both fuzzing and deep learning techniques to automate the generation and detection of Spectre gadgets. We first create a diverse set of Spectre-V1 gadgets by introducing perturbations to the known gadgets. Using mutational fuzzing, we produce a data set with more than 1 million Spectre-V1 gadgets which is the largest Spectre gadget data set built to date. Next, we conduct the first empirical usability study of Generative Adversarial Networks (GANs) in the context of assembly code generation without any human interaction. We introduce SpectreGAN which leverages masking implementation of GANs for both learning the gadget structures and generating new gadgets. This provides the first scalable solution to extend the variety of Spectre gadgets. Finally, we propose FastSpec which builds a classifier with the generated Spectre gadgets based on a novel high dimensional Neural Embeddings technique (BERT). For the case studies, we demonstrate that FastSpec discovers potential gadgets with a high success rate in OpenSSL libraries and Phoronix benchmarks. Further, FastSpec offers much greater flexibility and time-related performance gain compared to the existing tools and therefore can be used for gadget detection in large-scale software.

Over the past years, literature has shown that attacks exploiting the microarchitecture of modern processors pose a serious threat to user privacy. This is because applications leave distinct footprints in the processor, which malware can use to infer user activities. In this work, we show that these inference attacks can greatly be enhanced with advanced AI techniques. In particular, we focus on profiling the activity in the last-level cache (LLC) of ARM processors. We employ a simple Prime+Probe based monitoring technique to obtain cache traces, which we classify with deep learning methods including convolutional neural networks. We demonstrate our approach on an off-the-shelf Android phone by launching a successful attack from an unprivileged, zero-permission app in well under a minute. The app detects running applications, opened websites, and streaming videos with up to 98% accuracy and a profiling phase of at most 6 seconds. This is possible, as deep learning compensates measurement disturbances stemming from the inherently noisy LLC monitoring and unfavorable cache characteristics. In summary, our results show that thanks to advanced AI techniques, inference attacks are becoming alarmingly easy to execute in practice. This once more calls for countermeasures that confine microarchitectural leakage and protect mobile phone applications, especially those valuing the privacy of their users.