Related papers: Automatic Heap Layout Manipulation for Exploitatio…
Hierarchical Reinforcement Learning (HRL) agents often struggle with long-horizon visual planning due to their reliance on error-prone distance metrics. We propose Discrete Hierarchical Planning (DHP), a method that replaces continuous…
State-space search with explicit abstraction heuristics is at the state of the art of cost-optimal planning. These heuristics are inherently limited, nonetheless, because the size of the abstract space must be bounded by some, even if a…
We present skweak, a versatile, Python-based software toolkit enabling NLP developers to apply weak supervision to a wide range of NLP tasks. Weak supervision is an emerging machine learning paradigm based on a simple idea: instead of…
We study large-scale spatial systems that contain exogenous variables, e.g. environmental factors that are significant predictors in spatial processes. Building predictive models for such processes is challenging because the large numbers…
A novel approach to exploiting the log-convex structure present in many design problems is developed by modifying the classical Sequential Quadratic Programming (SQP) algorithm. The modified algorithm, Logspace Sequential Quadratic…
In this paper, we propose an algorithm that can be used on top of a wide variety of self-supervised (SSL) approaches to take advantage of hierarchical structures that emerge during training. SSL approaches typically work through some…
Artificial intelligence (AI) application domains consist of a mix of tensor operations with high and low arithmetic intensities (aka reuse). Hierarchical (i.e. compute along multiple levels of memory hierarchy) and heterogeneous (multiple…
Recently more attention has been given to adversarial attacks on neural networks for natural language processing (NLP). A central research topic has been the investigation of search algorithms and search constraints, accompanied by…
While deep spiking neural networks (SNNs) demonstrate superior performance, their deployment on resource-constrained neuromorphic hardware still remains challenging. Network pruning offers a viable solution by reducing both parameters and…
Meta-Reinforcement Learning (Meta-RL) learns optimal policies across a series of related tasks. A central challenge in Meta-RL is rapidly identifying which previously learned task is most similar to a new one, in order to adapt to it…
A resource leak occurs when a program fails to free some finite resource after it is no longer needed. Such leaks are a significant cause of real-world crashes and performance problems. Recent work proposed an approach to prevent resource…
Memory safety is an essential correctness property of software systems. For programs operating on linked heap-allocated data structures, the problem of proving memory safety boils down to analyzing the possible shapes of data structures,…
With the widespread deployment of Control-Flow Integrity (CFI), control-flow hijacking attacks, and consequently code reuse attacks, are significantly more difficult. CFI limits control flow to well-known locations, severely restricting…
Fully Homomorphic Encryption (FHE) is known to be extremely computationally-intensive, application-specific accelerators emerged as a powerful solution to narrow the performance gap. Nonetheless, due to the increasing complexities in FHE…
Long-horizon multimodal agents in open-world games must stay goal-directed across many low-level interactions under tight token and latency budgets. Existing approaches often trade off costly per-step reasoning against reactive execution…
Automated Exploit Generation (AEG) is a well-known difficult task, especially for heap vulnerabilities. Previous works first detected heap vulnerabilities and then searched for exploitable states by using symbolic execution and fuzzing…
Dynamic memory issues are hard to locate and may cost much of a development project's efforts and was repeatedly reported similarly afterwards independently by different persons. Verification as one formal method may proof a given program's…
This paper presents SHARP (Supercomputing for High-speed Avoidance and Reactive Planning), a proof-of-concept study demonstrating how high-performance computing (HPC) can enable millisecond-scale responsiveness in robotic control. While…
We introduce and study the problem of scrambler hacking, which is the procedure of quantum information extraction from and installation on a quantum scrambler given only partial access. This problem necessarily emerges from a central topic…
In a typical online resource allocation problem, we start with a fixed inventory of resources and make online allocation decisions in response to resource requests that arrive sequentially over a finite horizon. We consider settings where…