An official website of the United States government
Website fingerprinting attacks, which use statistical analysis on network traffic to compromise user privacy, have been shown to be effective even if the traffic is sent over anonymity-preserving networks such as Tor. The classical attack model used to evaluate website fingerprinting attacks assumes an on-path adversary, who can observe all traffic traveling between the user’s computer and the secure network. In this work we investigate these attacks under a different attack model, in which the adversary is capable of sending a small amount of malicious JavaScript code to the target user’s computer. The malicious code mounts a cache side-channel attack, which exploits the effects of contention on the CPU’s cache, to identify other websites being browsed. The effectiveness of this attack scenario has never been systematically analyzed, especially in the open-world model which assumes that the user is visiting a mix of both sensitive and non-sensitive sites. We show that cache website fingerprinting attacks in JavaScript are highly feasible. Specifically, we use machine learning techniques to classify traces of cache activity. Unlike prior works, which try to identify cache conflicts, our work measures the overall occupancy of the last-level cache. We show that our approach achieves high classification accuracy in both the open-world and the closed-world models. We further show that our attack is more resistant than network-based fingerprinting to the effects of response caching, and that our techniques are resilient both to network-based defenses and to side-channel countermeasures introduced to modern browsers as a response to the Spectre attack. To protect against cache-based website fingerprinting, new defense mechanisms must be introduced to privacy-sensitive browsers and websites. We investigate one such mechanism, and show that generating artificial cache activity reduces the effectiveness of the attack and completely eliminates it when used in the Tor Browser
more »
« less
Analyzing Cache Side Channels Using Deep Neural Networks
Cache side-channel attacks aim to breach the confidentiality of a computer system and extract sensitive secrets through CPU caches. In the past years, different types of side-channel attacks targeting a variety of cache architectures have been demonstrated. Meanwhile, different defense methods and systems have also been designed to mitigate these attacks. However, quantitatively evaluating the effectiveness of these attacks and defenses has been challenging. We propose a generic approach to evaluating cache side-channel attacks and defenses. Specifically, our method builds a deep neural network with its inputs as the adversary's observed information, and its outputs as the victim's execution traces. By training the neural network, the relationship between the inputs and outputs can be automatically discovered. As a result, the prediction accuracy of the neural network can serve as a metric to quantify how much information the adversary can obtain correctly, and how effective a defense solution is in reducing the information leakage under different attack scenarios. Our evaluation suggests that the proposed method can effectively evaluate different attacks and defenses.
more »
« less
- Award ID(s):
- 1814190
- PAR ID:
- 10207982
- Date Published:
- Journal Name:
- 34th Annual Computer Security Applications Conference (ACSAC)
- Page Range / eLocation ID:
- 174 to 186
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract—Recent work has demonstrated the security risk associated with micro-architecture side-channels. The cache timing side-channel is a particularly popular target due to its availability and high leakage bandwidth. Existing proposals for defending cache side-channel attacks either degrade cache performance and/or limit cache sharing, hence, should only be invoked when the system is under attack. A lightweight monitoring mechanism that detects malicious micro-architecture manipulation in realistic environments is essential for the judicious deployment of these defense mechanisms. In this paper, we propose PREDATOR, a cache side-channel attack detector that identifies cache events caused by an attacker. To detect side-channel attacks in noisy environments, we take advantage of the observation that, unlike non-specific noises, an active attacker alters victim’s micro-architectural states on security critical accesses and thus causes the victim extra cache events on those accesses. PREDATOR uses precise performance counters to collect detailed victim’s access information and analyzes location-based deviations. PREDATOR is capable of detecting five different attacks with high accuracy and limited performance overhead in complex noisy execution environments. PREDATOR remains effective even when the attacker slows the attack rate by 256 times. Furthermore, PREDATOR is able to accurately report details about the attack such as the instruction that accesses the attacked data. In the case of GnuPG RSA [20], PREDATOR can pinpoint the square/multiply operations in the Modulo-Reduce algorithm; and in the case of OpenSSL AES [45], it can identify the accesses to the Te-Table.more » « less
-
Last-Level Cache (LLC) attacks typically exploit timing side channels in hardware, and thus rely heavily on timers for their operation. Many proposed defenses against such side-channel attacks capitalize on this reliance. This paper presents PRIME+ABORT, a new cache attack which bypasses these defenses by not depending on timers for its function. Instead of a timing side channel, PRIME+ABORT leverages the Intel TSX hardware widely available in both server- and consumer-grade processors. This work shows that PRIME+ABORT is not only invulnerable to important classes of defenses, it also outperforms state-of-the-art LLC PRIME+PROBE attacks in both accuracy and efficiency, having a maximum detection speed (in events per second) 3× higher than LLC PRIME+PROBE on Intel’s Skylake architecture while producing fewer false positives.more » « less
-
Federated learning collaboratively trains a neural network on a global server, where each local client receives the current global model weights and sends back parameter updates (gradients) based on its local private data. The process of sending these model updates may leak client’s private data information. Existing gradient inversion attacks can exploit this vulnerability to recover private training instances from a client’s gradient vectors. Recently, researchers have proposed advanced gradient inversion techniques that existing defenses struggle to handle effectively. In this work, we present a novel defense tailored for large neural network models. Our defense capitalizes on the high dimensionality of the model parameters to perturb gradients within a subspace orthogonal to the original gradient. By leveraging cold posteriors over orthogonal subspaces, our defense implements a refined gradient update mechanism. This enables the selection of an optimal gradient that not only safeguards against gradient inversion attacks but also maintains model utility. We conduct comprehensive experiments across three different datasets and evaluate our defense against various state-of-the-art attacks and defenses. Code is available at https://censor-gradient.github.io.more » « less
-
Secure architectures are becoming an increasingly common demand. This is due in large part to the rise of cloud computing, as users are trusting their data with hardware that they do not own. Unfortunately, many secure computation and isolation techniques are still susceptible to side-channel attacks. While various defenses to side-channel attacks exist, each tends to be targeted to a specific vulnerability and comes with a high runtime overhead, making it difficult to combine these defenses together in a performant manner.This work proposes an efficient design for preventing a large range of cache side-channel attacks by leveraging a near-memory processing (NMP) architecture. Specifically, the proposed design stores all sensitive data in isolated NMP vaults and performs all computation involving that sensitive data on NMP cores. Our approach eliminates possible cache side-channels while also minimizing runtime overhead when the parallelizability of NMP architecture is leveraged. Simulation results from a cycle-accurate architecture model shows that offloading secure computation to NMP cores can have as little as 0.26% overhead.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1145/3274694.3274715
