相关论文: "It's a Trap!"-How Speculation Invariance Can Be A…

Gradient inversion attacks are an ubiquitous threat in federated learning as they exploit gradient leakage to reconstruct supposedly private training data. Recent work has proposed to prevent gradient leakage without loss of model utility…

Security can be seen as an optimisation objective in NoC resource management, and as such poses trade-offs against other objectives such as real-time schedulability. In this paper, we show how to increase NoC resilience against a concrete…

Building advanced machine learning (ML) models requires expert knowledge and many trials to discover the best architecture and hyperparameter settings. Previous work demonstrates that model information can be leveraged to assist other…

Modern language models have enabled the development of agentic systems that achieve strong performance on reasoning-intensive tasks. Unfortunately, this has come with a security cost; these systems are vulnerable to prompt injection, a…

The cognitive interference channel with confidential messages (CICC) proposed by Liang et. al. is investigated. When the security is considered in coding systems, it is well known that the sender needs to use a stochastic encoding to avoid…

Variational inference has become one of the most widely used methods in latent variable modeling. In its basic form, variational inference employs a fully factorized variational distribution and minimizes its KL divergence to the posterior.…

A common countermeasure against side-channel attacks on secret key cryptographic implementations is $d$th-order masking, which splits each sensitive variable into $d+1$ random shares. In this paper, maximal leakage bounds on the probability…

Deep neural networks (DNNs) are highly susceptible to adversarial examples--subtle perturbations applied to inputs that are often imperceptible to humans yet lead to incorrect model predictions. In black-box scenarios, however, existing…

Prescriptive process monitoring methods seek to improve the performance of a process by selectively triggering interventions at runtime (e.g., offering a discount to a customer) to increase the probability of a desired case outcome (e.g., a…

When users make personal privacy choices, correlation between their data can cause inadvertent leakage about users who do not want to share their data by other users sharing their data. As a solution, we consider local redaction mechanisms.…

Counterfactual explanations are emerging as an attractive option for providing recourse to individuals adversely impacted by algorithmic decisions. As they are deployed in critical applications (e.g. law enforcement, financial lending), it…

The massive trend toward embedded systems introduces new security threats to prevent. Malicious firmware makes it easier to launch cyberattacks against embedded systems. Systems infected with malicious firmware maintain the appearance of…

This paper investigates the so-called leakage effect of trading strategies generated functionally from rank-dependent portfolio generating functions. This effect measures the loss in wealth of trading strategies due to renewing the…

The cloud model's dependence on massive parallelism and resource sharing exacerbates the security challenge of timing side-channels. Timing Information Flow Control (TIFC) is a novel adaptation of IFC techniques that may offer a way to…

The severity of recent vulnerabilities discovered on modern CPUs, e.g., Spectre [1], highlights how information leakage can have devas-tating effects to the security of computer systems. At the same time, it suggests that confidentiality…

Data-driven neural path planners are attracting increasing interest in the robotics community. However, their neural network components typically come as black boxes, obscuring their underlying decision-making processes. Their black-box…

Irregular codes are bottlenecked by memory and communication latency. Decoupled access/execute (DAE) is a common technique to tackle this problem. It relies on the compiler to separate memory address generation from the rest of the program,…

Autoregressive decoding is bottlenecked by its sequential nature. Speculative decoding has become a standard way to accelerate inference by using a fast draft model to predict upcoming tokens from a slower target model, and then verifying…

Caches have been used to construct various types of covert and side channels to leak information. Most existing cache channels exploit the timing difference between cache hits and cache misses. However, we introduce a new and broader…

Fault injection attacks (FIA) pose significant security threats to embedded systems as they exploit weaknesses across multiple layers, including system software, instruction set architecture (ISA), microarchitecture, and physical hardware.…