Multi-factor authentication

Multi-factor authentication (MFA; two-factor authentication, or 2FA, along with similar terms) is an electronic authentication method in which a user is granted access to a website or application only after successfully presenting two or more pieces of evidence (or factors) to an authentication mechanism. MFA protects personal data—which may include personal identification or financial assets—from being accessed by an unauthorized third party that may have been able to discover, for example, a single password. A third-party authenticator (TPA) app enables two-factor authentication, usually by showing a randomly generated and frequently changing code to use for authentication. Factors Authentication takes place when someone tries to log into a computer resource (such as a computer network, device, or application). The resource requires the user to supply the identity by which the user is known to the resource, along with evidence of the authenticity of the user's claim to

Secure Communications over Insecure Channels Using an Authenticated Channel

Sylvain Pasini

A secure communication over an insecure channel without any prior exchanged key can be established with the help of an authentication step to exchange a public key and then using public-key cryptography such as RSA. In this work, we concentrate on message authentication protocols which require an extra authenticated channel. We also recall biometrics-based systems which are hard to implement and distance bounding-based authentication systems which are limited to closer communications. We sketch three generic attacks against any message authentication protocol, conclude on their maximal security, and study the security of some protocols. Finally, we propose a new protocol which achieves the same security level as that of SSH and GPG, but using much less authenticated bits.

2005

Understanding Deep Neural Networks using Adversarial Attacks

Krishna Kanth Nakka

Deep Neural Networks (DNNs) have achieved great success in a wide range of applications, such as image recognition, object detection, and semantic segmentation. Even thoughthe discriminative power of DNNs is nowadays unquestionable, serious concerns have arised ever since DNNs have shown to be vulnerable to adversarial examples craftedby adding imperceptible perturbations to clean images. The implications of these malicious attacks are even more significant for DNNs deployed in real-world systems, e.g.,autonomous driving and biometric authentication. Consequently, an intriguing question that we aim to understand is the underlying behavior of DNNs to adversarial attacks.This thesis contributes to a better understanding of the mechanism of adversarial attacks on DNNs. Our main contributions are broadly in two directions: (1) we proposeinterpretable architectures first to understand the reasons for the success of adversarial attacks and then to improve the robustness of DNNs; (2) we design intuitive adversarialattacks to both mislead and use as a tool to expand our present understanding of DNNs' internal workings and their limitations. In the first direction, we introduce deep architectures that allow humans to interpret the reasoning process of DNNs prediction. Specifically, we incorporate Bag-of-visual-wordsrepresentations from the pre-deep learning era into DNNs using an attention scheme. We find key reasons for adversarial attack success and use these insights to propose anadversarial defense by maximally separating the latent features of discriminative regions while minimizing the contribution of non-discriminative regions in the final prediction.The second direction deals with the design of adversarial attacks to understand DNNs' limitations in a real-world environment. To begin with, we show that existing state-of-the-art semantic segmentation networks that achieve superior performance by exploiting the context are highly susceptible to indirect local attacks. Furthermore, we demonstrate the existence of universal directional perturbations that are quasi-independent of the input template but still successfully fool unknown siamese-based visual object trackers. We then identify that the mid-level filter banks across different backbones bear strong similarities and thus can be potential common ground for attack. We, therefore, learn a generator that disrupts mid-level features with high transferability across different target architectures, datasets, and tasks. In short, our attacks highlight critical vulnerabilities of DNNs, which make their deployment challenging in the real-world environment, even in the extreme case when the attacker is unaware of the target architecture or the targetdata used to train it.Furthermore, we go beyond fooling networks and demonstrate the usefulness of adversarial attacks for studying the internal disentangled representations in self-supervised 3D pose estimation networks. We observe that adversarial manipulation of appearance information in the input image alters the pose output, indicating that the pose code contains appearance information and disentanglement is far from complete. Besides the above contributions, an underlying theme that arises multiple times in this thesis is counteracting the adversarial attacks by detecting them.

EPFL2022

Understanding Deep Neural Networks using Adversarial Attacks

Krishna Kanth Nakka

EPFL2022

Metamodeling techniques for VAN critical factors identification

Secure Communications over Insecure Channels Using an Authenticated Channel

Understanding Deep Neural Networks using Adversarial Attacks

Understanding Deep Neural Networks using Adversarial Attacks

Secure Communications over Insecure Channels Using an Authenticated Channel

Metamodeling techniques for VAN critical factors identification