Related papers: Designing Trustworthy Layered Attestations
This position paper argues that enforcing LLM agent safety within a single abstraction layer is not merely suboptimal but categorically insufficient for deployed LLM agents -- a structural consequence of how agent execution works, not a…
The increasing use of machine-learning (ML) enabled systems in critical tasks fuels the quest for novel verification and validation techniques yet grounded in accepted system assurance principles. In traditional system development,…
Adversarial examples pose a security risk as they can alter decisions of a machine learning classifier through slight input perturbations. Certified robustness has been proposed as a mitigation where given an input $\mathbf{x}$, a…
Certified defenses against adversarial attacks offer formal guarantees on the robustness of a model, making them more reliable than empirical methods such as adversarial training, whose effectiveness is often later reduced by unseen…
Heterogeneous computing, which incorporates GPUs, NPUs, and FPGAs, is increasingly utilized to improve the efficiency of computer systems. However, this shift has given rise to significant security and privacy concerns, especially when the…
In cloud computing, data processing is delegated to a remote party for efficiency and flexibility reasons. A practical user requirement usually is that the confidentiality and integrity of data processing needs to be protected. In the…
The growing pervasiveness of Internet of Things (IoT) expands the attack surface by connecting more and more attractive attack targets, i.e. embedded devices, to the Internet. One key component in securing these devices is software…
Linux systems are integral to the infrastructure of modern computing environments, necessitating robust security measures to prevent unauthorized access. Privilege escalation attacks represent a significant threat, typically allowing…
As an essential technology underpinning trusted computing, the trusted execution environment (TEE) allows one to launch computation tasks on both on- and off-premises data while assuring confidentiality and integrity. This article provides…
We propose a protocol that explores a synergy between two TEE implementations: it brings SGX-like remote attestation to SEV VMs. We use the notion of a \emph{trusted guest owner}, implemented as an SGX enclave, to deploy, attest, and…
The increasing use of Machine Learning (ML) components embedded in autonomous systems -- so-called Learning-Enabled Systems (LESs) -- has resulted in the pressing need to assure their functional safety. As for traditional functional safety,…
Neural networks have demonstrated considerable success on a wide variety of real-world problems. However, networks trained only to optimize for training accuracy can often be fooled by adversarial examples - slightly perturbed inputs that…
We present a framework for verifying the deterministic structured computations surrounding a large language model rather than the model itself, extending a Lean 4 trust-boundary architecture to the generic interfaces of modern LLM…
Future communication networks such as 5G are expected to support end-to-end delivery of services for several vertical markets with diverging requirements. Network slicing is a key construct that is used to provide end to end logical virtual…
Recently, techniques have been developed to provably guarantee the robustness of a classifier to adversarial perturbations of bounded L_1 and L_2 magnitudes by using randomized smoothing: the robust classification is a consensus of base…
Hundreds of defenses have been proposed to make deep neural networks robust against minimal (adversarial) input perturbations. However, only a handful of these defenses held up their claims because correctly evaluating robustness is…
Confidential computing alleviates the concerns of distrustful customers by removing the cloud provider from their trusted computing base and resolves their disincentive to migrate their workloads to the cloud. This is facilitated by new…
Security risk assessment is essential in establishing the trustworthiness and reliability of modern systems. While various security risk assessment approaches exist, prevalent applications are "pen and paper" implementations that -- even if…
Large language models (LLMs) are vulnerable to adversarial attacks that add malicious tokens to an input prompt to bypass the safety guardrails of an LLM and cause it to produce harmful content. In this work, we introduce erase-and-check,…
The structures for the expression of fault-tolerance provisions into the application software are the central topic of this paper. Structuring techniques answer the questions "How to incorporate fault-tolerance in the application layer of a…