Adversarial Scrutiny of Evidentiary Statistical Software

Evidentiary Implications of Potential Security Weaknesses in Forensic Software

Computer forensic software is used by lawyers and law enforcement to collect and preserve data in a “forensic image” so that it can be analyzed without changing the original media, and to preserve the chain of custody of the evidence. To the extent there are vulnerabilities in this software, an attacker may be able to hide or alter the data available to a forensic analyst, causing courts to ren...

Software-Defined Adversarial Trajectory Sampling

Today’s routing protocols critically rely on the assumption that the underlying hardware is trusted. Given the increasing number of attacks on network devices, and recent reports on hardware backdoors this assumption has become questionable. Indeed, with the critical role computer networks play today, the contrast between our security assumptions and reality is problematic. This paper presents ...

On the (Statistical) Detection of Adversarial Examples

Machine Learning (ML) models are applied in a variety of tasks such as network intrusion detection or malware classification. Yet, these models are vulnerable to a class of malicious inputs known as adversarial examples. These are slightly perturbed inputs that are classified incorrectly by the ML model. The mitigation of these adversarial inputs remains an open problem. As a step towards a mod...

Towards Adversarial Reasoning in Statistical Relational Domains

Statistical relational artificial intelligence combines first-order logic and probability in order to handle the complexity and uncertainty present in many real-world domains. However, many real-world domains also include multiple agents that cooperate or compete according to their diverse goals. In order to handle such domains, an autonomous agent must also consider the actions of other agents...

Dealing with Evidentiary Deficiency