BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Tianxiang Dai

Tianxiang Dai appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Cryptography and SecurityComputation and Language

Catalog footprint

What is connected

3works
2topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

3 published item(s)

preprint2026arXiv

Language models fail at extended rule following

Large language models are highly capable of answering difficult questions by retrieving, recombining, and attending to information in long contexts. For agentic tasks, an additional capability is required: the preservation of an exact state while repeatedly applying rules. We find that this reliability is absent across language models. To demonstrate, we query 126 leading model variants with the task of counting a long string of repeated characters, and we find they all cannot accurately count above a model-dependent, syntax-sensitive counting capacity threshold. Failures are abrupt and persist even with increasing model size, inference time computation, and external tool. Mechanistic probing indicates that models use a finite number of internal states to mimic counting as a rule and fail once these states are exhausted. Furthermore, such states are the basis for performing complex tasks beyond counting. These results indicate that fundamentally new model architectures are required for autonomous agents to achieve truly reliable rule following capabilities.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

From IP to transport and beyond: cross-layer attacks against applications

We perform the first analysis of methodologies for launching DNS cache poisoning: manipulation at the IP layer, hijack of the inter-domain routing and probing open ports via side channels. We evaluate these methodologies against DNS resolvers in the Internet and compare them with respect to effectiveness, applicability and stealth. Our study shows that DNS cache poisoning is a practical and pervasive threat. We then demonstrate cross-layer attacks that leverage DNS cache poisoning for attacking popular systems, ranging from security mechanisms, such as RPKI, to applications, such as VoIP. In addition to more traditional adversarial goals, most notably impersonation and Denial of Service, we show for the first time that DNS cache poisoning can even enable adversaries to bypass cryptographic defences: we demonstrate how DNS cache poisoning can facilitate BGP prefix hijacking of networks protected with RPKI even when all the other networks apply route origin validation to filter invalid BGP announcements. Our study shows that DNS plays a much more central role in the Internet security than previously assumed. We recommend mitigations for securing the applications and for preventing cache poisoning.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

The Hijackers Guide To The Galaxy: Off-Path Taking Over Internet Resources

Internet resources form the basic fabric of the digital society. They provide the fundamental platform for digital services and assets, e.g., for critical infrastructures, financial services, government. Whoever controls that fabric effectively controls the digital society. In this work we demonstrate that the current practices of Internet resources management, of IP addresses, domains, certificates and virtual platforms are insecure. Over long periods of time adversaries can maintain control over Internet resources which they do not own and perform stealthy manipulations, leading to devastating attacks. We show that network adversaries can take over and manipulate at least 68% of the assigned IPv4 address space as well as 31% of the top Alexa domains. We demonstrate such attacks by hijacking the accounts associated with the digital resources. For hijacking the accounts we launch off-path DNS cache poisoning attacks, to redirect the password recovery link to the adversarial hosts. We then demonstrate that the adversaries can manipulate the resources associated with these accounts. We find all the tested providers vulnerable to our attacks. We recommend mitigations for blocking the attacks that we present in this work. Nevertheless, the countermeasures cannot solve the fundamental problem - the management of the Internet resources should be revised to ensure that applying transactions cannot be done so easily and stealthily as is currently possible.

0 citations0 reviewsNo code linkedOpen access