Related papers: Ghost: A Uniform and General-Purpose Proxy Impleme…
Language models remain vulnerable to prompt injection attacks despite extensive safety training. We trace this failure to role confusion: models infer the source of text based on how it sounds, not where it actually comes from. A command…
A security policy states the acceptable actions of an information system, as the actions bear on security. There is a pressing need for organizations to declare their security policies, even informal statements would be better than the…
Dataflow languages provide natural support for specifying constraints between objects in dynamic applications, where programs need to react efficiently to changes of their environment. Researchers have long investigated how to take…
Latency attacks against object detection represent a variant of adversarial attacks that aim to inflate the inference time by generating additional ghost objects in a target image. However, generating ghost objects in the black-box scenario…
In this dissertation, we present LaSCO, the Language for Security Constraints on Objects, a new approach to expressing security policies using policy graphs and present a method for enforcing policies so expressed. Other approaches for…
Universal goal hijacking is a kind of prompt injection attack that forces LLMs to return a target malicious response for arbitrary normal user prompts. The previous methods achieve high attack performance while being too cumbersome and…
Generalization outside the scope of one's training data requires leveraging prior knowledge about the effects that transfer, and the effects that don't, between different data sources. Transfer learning is a framework for specifying and…
Training and fine-tuning large-scale language models largely benefit from collaborative learning, but the approach has been proven vulnerable to gradient inversion attacks (GIAs), which allow adversaries to reconstruct private training data…
Typestates are state machines used in object-oriented programming to specify and verify correct order of method calls on an object. To avoid inconsistent object states, typestates enforce linear typing, which eliminates - or at best limits…
Application security traditionally strongly relies upon security of the underlying operating system. However, operating systems often fall victim to software attacks, compromising security of applications as well. To overcome this…
This paper proposes a novel approach to object detection on drone imagery, namely Multi-Proxy Detection Network with Unified Foreground Packing (UFPMP-Det). To deal with the numerous instances of very small scales, different from the common…
Fingerprint recognition systems are widely deployed for authentication and forensic applications, but the security of stored fingerprint data remains a critical vulnerability. While many systems avoid storing raw fingerprint images in favor…
We propose a prototype-based federated learning method designed for embedding networks in classification or verification tasks. Our focus is on scenarios where each client has data from a single class. The main challenge is to develop an…
We introduce UFO, an innovative UI-Focused agent to fulfill user requests tailored to applications on Windows OS, harnessing the capabilities of GPT-Vision. UFO employs a dual-agent framework to meticulously observe and analyze the…
Network objects are a simple and natural abstraction for distributed object-oriented programming. Languages that support network objects, however, often leave synchronization to the user, along with its associated pitfalls, such as data…
Open-vocabulary human-object interaction (HOI) detection requires recognizing interaction phrases that may not appear as annotated categories during training. Recent vision-language HOI detectors improve semantic transfer by matching…
Diffusion models have demonstrated their capability to synthesize high-quality and diverse images from textual prompts. However, simultaneous control over both global contexts (e.g., object layouts and interactions) and local details (e.g.,…
Temporal prefetching shows promise for handling irregular memory access patterns, which are common in data-dependent and pointer-based data structures. Recent studies introduced on-chip metadata storage to reduce the memory traffic caused…
We introduce an object-oriented framework for parallel programming, which is based on the observation that programming objects can be naturally interpreted as processes. A parallel program consists of a collection of persistent processes…
Modern mobile applications rely on hidden interactions--gestures without visual cues like long presses and swipes--to provide functionality without cluttering interfaces. While experienced users may discover these interactions through prior…