相关论文: Danger Invariants
Deep neural networks are facing a potential security threat from adversarial examples, inputs that look normal but cause an incorrect classification by the deep neural network. For example, the proposed threat could result in hand-written…
This paper develops a safety analysis method for stochastic systems that is sensitive to the possibility and severity of rare harmful outcomes. We define risk-sensitive safe sets as sub-level sets of the solution to a non-standard optimal…
This paper proposes a safety analysis method that facilitates a tunable balance between the worst-case and risk-neutral perspectives. First, we define a risk-sensitive safe set to specify the degree of safety attained by a stochastic…
The procedure to find gauge invariant variables for two-parameter nonlinear perturbations in general relativity is considered. For each order metric perturbation, we define the variable which is defined by the appropriate combination with…
Safe reinforcement learning has traditionally relied on predefined constraint functions to ensure safety in complex real-world tasks, such as autonomous driving. However, defining these functions accurately for varied tasks is a persistent…
The continuous increase in malware samples, both in sophistication and number, presents many challenges for organizations and analysts, who must cope with thousands of new heterogeneous samples daily. This requires robust methods to quickly…
Neural ODEs are increasingly used as continuous-time models for scientific and sensor data, but unconstrained neural ODEs can drift and violate domain invariants (e.g., conservation laws), yielding physically implausible solutions. In turn,…
We introduce a novel, practically relevant variation of the anomaly detection problem in multi-variate time series: intrinsic anomaly detection. It appears in diverse practical scenarios ranging from DevOps to IoT, where we want to…
This paper assesses the transient stability of a synchronous machine connected to an infinite bus through the notion of invariant sets. The problem of computing a conservative approximation of the maximal positive invariant set is…
Stateflow models are complex software models, often used as part of industrial safety-critical software solutions designed with Matlab Simulink. Being part of safety-critical solutions, these models require the application of rigorous…
Static Analysis (SA) tools are used to identify potential weaknesses in code and fix them in advance, while the code is being developed. In legacy codebases with high complexity, these rules-based static analysis tools generally report a…
In this work, we describe a new software model-checking algorithm called GPS. GPS treats the task of model checking a program as a directed search of the program states, guided by a compositional, summary-based static analysis. The…
Static Application Security Testing (SAST) is a popular quality assurance technique in software engineering. However, integrating SAST tools into industry-level product development and security assessment poses various technical and…
Threat hunting is sifting through system logs to detect malicious activities that might have bypassed existing security measures. It can be performed in several ways, one of which is based on detecting anomalies. We propose an unsupervised…
Over 70% of security vulnerabilities in critical software systems today result from memory safety violations. To address this challenge, fuzzing and static analysis are widely used automated methods to discover such vulnerabilities. Fuzzing…
Ensuring safety in industrial control systems usually involves imposing constraints at the design stage of the control algorithm. Enforcing constraints is challenging if the underlying functional form is unknown. The challenge can be…
Invariants withstand transformations and, therefore, represent the essence of objects or phenomena. In mathematics, transformations often constitute a group action. Since the 19th century, studying the structure of various types of…
Optimizing noisy functions online, when evaluating the objective requires experiments on a deployed system, is a crucial task arising in manufacturing, robotics and many others. Often, constraints on safe inputs are unknown ahead of time,…
Sophisticated attackers find bugs in software, evaluate their exploitability, and then create and launch exploits for bugs found to be exploitable. Most efforts to secure software attempt either to eliminate bugs or to add mitigations that…
A high-gain observer is used for a class of feedback linearisable nonlinear systems to synthesize safety-preserving controllers over the observer output. A bound on the distance between trajectories under state and output feedback is…