اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدSample Efficient Detection and Classification of Adversarial Attacks via Self-Supervised Embeddings
69
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Adversarial robustness of deep models is pivotal in ensuring safe deployment in real world settings, but most modern defenses have narrow scope and expensive costs. In this paper, we propose a self-supervised method to detect adversarial attacks and classify them to their respective threat models, based on a linear model operating on the embeddings from a pre-trained self-supervised encoder. We use a SimCLR encoder in our experiments, since we show the SimCLR embedding distance is a good proxy for human perceptibility, enabling it to encapsulate many threat models at once. We call our method SimCat since it uses SimCLR encoder to catch and categorize various types of adversarial attacks, including L_p and non-L_p evasion attacks, as well as data poisonings. The simple nature of a linear classifier makes our method efficient in both time and sample complexity. For example, on SVHN, using only five pairs of clean and adversarial examples computed with a PGD-L_inf attack, SimCats detection accuracy is over 85%. Moreover, on ImageNet, using only 25 examples from each threat model, SimCat can classify eight different attack types such as PGD-L_2, PGD-L_inf, CW-L_2, PPGD, LPA, StAdv, ReColor, and JPEG-L_inf, with over 40% accuracy. On STL10 data, we apply SimCat as a defense against poisoning attacks, such as BP, CP, FC, CLBD, HTBD, halving the success rate while using only twenty total poisons for training. We find that the detectors generalize well to unseen threat models. Lastly, we investigate the performance of our detection method under adaptive attacks and further boost its robustness against such attacks via adversarial training.
قيم البحث
اقرأ أيضاً
Malware remains a big threat to cyber security, calling for machine learning based malware detection. While promising, such detectors are known to be vulnerable to evasion attacks. Ensemble learning typically facilitates countermeasures, while attack
ers can leverage this technique to improve attack effectiveness as well. This motivates us to investigate which kind of robustness the ensemble defense or effectiveness the ensemble attack can achieve, particularly when they combat with each other. We thus propose a new attack approach, named mixture of attacks, by rendering attackers capable of multiple generative methods and multiple manipulation sets, to perturb a malware example without ruining its malicious functionality. This naturally leads to a new instantiation of adversarial training, which is further geared to enhancing the ensemble of deep neural networks. We evaluate defenses using Android malware detectors against 26 different attacks upon two practical datasets. Experimental results show that the new adversarial training significantly enhances the robustness of deep neural networks against a wide range of attacks, ensemble methods promote the robustness when base classifiers are robust enough, and yet ensemble attacks can evade the enhanced malware detectors effectively, even notably downgrading the VirusTotal service.
Neural networks are increasingly used in security applications for intrusion detection on industrial control systems. In this work we examine two areas that must be considered for their effective use. Firstly, is their vulnerability to adversarial at
tacks when used in a time series setting. Secondly, is potential over-estimation of performance arising from data leakage artefacts. To investigate these areas we implement a long short-term memory (LSTM) based intrusion detection system (IDS) which effectively detects cyber-physical attacks on a water treatment testbed representing a strong baseline IDS. For investigating adversarial attacks we model two different white box attackers. The first attacker is able to manipulate sensor readings on a subset of the Secure Water Treatment (SWaT) system. By creating a stream of adversarial data the attacker is able to hide the cyber-physical attacks from the IDS. For the cyber-physical attacks which are detected by the IDS, the attacker required on average 2.48 out of 12 total sensors to be compromised for the cyber-physical attacks to be hidden from the IDS. The second attacker model we explore is an $L_{infty}$ bounded attacker who can send fake readings to the IDS, but to remain imperceptible, limits their perturbations to the smallest $L_{infty}$ value needed. Additionally, we examine data leakage problems arising from tuning for $F_1$ score on the whole SWaT attack set and propose a method to tune detection parameters that does not utilise any attack data. If attack after-effects are accounted for then our new parameter tuning method achieved an $F_1$ score of 0.811$pm$0.0103.
False Data Injection (FDI) attacks are a common form of Cyber-attack targetting smart grids. Detection of stealthy FDI attacks is impossible by the current bad data detection systems. Machine learning is one of the alternative methods proposed to det
ect FDI attacks. This paper analyzes three various supervised learning techniques, each to be used with three different feature selection (FS) techniques. These methods are tested on the IEEE 14-bus, 57-bus, and 118-bus systems for evaluation of versatility. Accuracy of the classification is used as the main evaluation method for each detection technique. Simulation study clarify the supervised learning combined with heuristic FS methods result in an improved performance of the classification algorithms for FDI attack detection.
Few-shot classifiers excel under limited training samples, making them useful in applications with sparsely user-provided labels. Their unique relative prediction setup offers opportunities for novel attacks, such as targeting support sets required t
o categorise unseen test samples, which are not available in other machine learning setups. In this work, we propose a detection strategy to identify adversarial support sets, aimed at destroying the understanding of a few-shot classifier for a certain class. We achieve this by introducing the concept of self-similarity of a support set and by employing filtering of supports. Our method is attack-agnostic, and we are the first to explore adversarial detection for support sets of few-shot classifiers to the best of our knowledge. Our evaluation of the miniImagenet (MI) and CUB datasets exhibits good attack detection performance despite conceptual simplicity, showing high AUROC scores. We show that self-similarity and filtering for adversarial detection can be paired with other filtering functions, constituting a generalisable concept.
Visual object tracking is an important task that requires the tracker to find the objects quickly and accurately. The existing state-ofthe-art object trackers, i.e., Siamese based trackers, use DNNs to attain high accuracy. However, the robustness of
visual tracking models is seldom explored. In this paper, we analyze the weakness of object trackers based on the Siamese network and then extend adversarial examples to visual object tracking. We present an end-to-end network FAN (Fast Attack Network) that uses a novel drift loss combined with the embedded feature loss to attack the Siamese network based trackers. Under a single GPU, FAN is efficient in the training speed and has a strong attack performance. The FAN can generate an adversarial example at 10ms, achieve effective targeted attack (at least 40% drop rate on OTB) and untargeted attack (at least 70% drop rate on OTB).
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
