Tootfinder

Opt-in global Mastodon full text search. Join the index!

@arXiv_csCR_bot@mastoxiv.page
2026-07-24 07:50:41

Enhancing Attack Detection Capabilities in BACnet/IP Networks Using Machine-Learning Models
Derek Manzella, John D. Hastings
arxiv.org/abs/2607.20686 arxiv.org/pdf/2607.20686 arxiv.org/html/2607.20686
arXiv:2607.20686v1 Announce Type: new
Abstract: Building Automation Systems (BAS) manage critical building functions using protocols such as BACnet/IP, yet defenders have limited tooling and few labeled datasets for detecting BACnet-specific attacks. This work addresses these gaps through three contributions. First, CISA's Zeek BACnet parser is modified to produce a unified per-packet log, simplifying feature engineering for machine-learning (ML) pipelines. Second, a simulated BACnet/IP testbed is developed using bacpypes3 to model a small commercial HVAC system with physics-based device behavior, schedule-aware controller logic, and per-packet attack labeling. Third, five unsupervised anomaly detection models are evaluated using baseline traffic and six BACnet attack types, including denial of service, reconnaissance, property tampering, and false data injection. Results show that One-Class SVM achieved the strongest overall performance, with an average F1 score of 0.864 across all attacks and F1 scores above 0.99 for high-volume denial-of-service and reconnaissance attacks. Detection is much stronger for high-volume attacks, such as DoS attacks and reconnaissance, than stealthier techniques such as tampering and false data injection, which scored around 77%.
toXiv_bot_toot

@seeingwithsound@mas.to
2026-07-20 10:24:13

Assisting the last mile with smart glasses: towards user-centric LLM prompt engineering for visually impaired people #AI

@sperbsen@discuss.systems
2026-07-15 19:38:59

I know I’m late to the party to @…’s post “Is it ethical to use AI?”, where she argues that “AI is just technology”. It’s been festering inside me, and Martin Fowler’s mention of the article that calls AI “a technology that is so powerful and so useful”, and therefore “there’s no ethical gain from renouncing the use of AI”. (Especially as both have provided th…

AdaptHealth says attackers used social engineering to breach its systems
and steal sensitive patient data,
including passwords associated with insurance billing.
The medical equipment company disclosed the attack to the Securities and Exchange Commission (SEC) on Thursday,
noting that attackers accessed internal patient management systems, document storage platforms,
and external electronic health record system portals.
The attack targeted an unwitting thi…

@Techmeme@techhub.social
2026-07-02 13:15:41

Microsoft establishes an organization with 6,000 staff specializing in engineering, corporate training, and management to support businesses with AI deployments (Todd Bishop/GeekWire)
geekwire.com/2026/microsoft-an

@grist@fosstodon.org
2026-09-09 23:49:53

Grist’s custom widget framework, full API access, and self-hosting options give engineering teams the infrastructure to build requirements traceability systems on their own terms. getgrist.com/case-studies/how-…

@Techmeme@techhub.social
2026-06-29 10:55:35

Google VP of Security Engineering Heather Adkins warns the EU's DMA proposals to open Android and Search could lead to a significant rise in fraud within weeks (Matt Burgess/Wired)
wired.com/story/top-google-sec

@metacurity@infosec.exchange
2026-08-10 14:02:28

Good lord, you are not going to believe the massive amount of cybersecurity news you might have missed since just Friday, so check out today's Metacurity for the top developments, including
--DPRK's Kimsuky built an in-house AI toolkit to power cyberattacks,
--Chinese components in UK military drones secretly transmitted data,
--California city declares emergency after cyberattack disrupts 911 services,
--Turkey's new cyber law sparks fears of sweeping digital censorship,
--OpenAI's Hugging Face hack reveals deeper AI safety failures,
--Anthropic makes Claude Code's autonomous mode the default,
--AI agent hacks gym booking system without being told to,
--Military supplier discloses phishing breach exposing sensitive defense data,
--Iranian water hacks revive push for EPA cyber authority,
--Levi Strauss says social engineering attack breached company systems,
--Australian court users' data posted on dark web,
--Framework customer data stolen in upstream Metabase breach,
--Major law firms paid $28m in Luna Moth ransomware attacks,
--Former SK Hynix employee jailed for leaking chip secrets to China,
--S. Korean opposition apologizes for breach affecting 17,000 members,
--S. Korean teams dominate DEF CON hacking finals,
--Breach at S. Korea's 3Pro TV exposes 460,000 customer records,
--Serbian entrepreneur arrested over alleged hacking of Croatian government systems,
--One-third of UK manufacturers hit by cyberattacks,
--Poland details second Russian cyberattack on power grid,
--Researchers' email honeypot captures hundreds of thousands of misdirected messages,
--Ransomware gangs increasingly target midlevel managers,
--Oklahoma Manufacturing Alliance hit by Booba ransomware attack,
--Thai agencies consider MFA after widespread government data leaks,
--Vintage computer collectors preserve the machines that built the digital age,
--Meta smart glasses face growing privacy backlash,
--Amazon backs massive gas-powered plant for Texas AI data center,
--OpenAI touts AI productivity while employees work 90-hour weeks
metacurity.com/dprks-kimsuky-b

@arXiv_csAR_bot@mastoxiv.page
2026-08-14 07:31:47

Dryas: A Reprogrammable Engine for High-Speed Interconnect Tracing and Analysis
Manuel Br\"ochin, Tom Kuchler, Michael Giardino, David Cock, Timothy Roscoe
arxiv.org/abs/2608.12934 arxiv.org/pdf/2608.12934 arxiv.org/html/2608.12934
arXiv:2608.12934v1 Announce Type: new
Abstract: The proliferation of heterogeneous components in modern computing systems has been accompanied by new higher bandwidth and lower latency interconnects. These interfaces and protocols are enormously complex and the process of developing, debugging, and analyzing FPGA-based implementations requires significant engineering work. Moreover, once a functional implementation is completed, optimization of the controller and associated software requires processing potentially hundreds of gigabytes of trace data.
In this paper, we present Dryas, an open source tool for analyzing such an interconnect. We developed our tool, using minimal hardware resources, alongside an FPGA implementation of a very high speed, low latency (30~GiB/s, 200~ns) interconnect. With our run-time reprogrammable overlay engine we can inspect this interconnect to find rare, complex, or transient events even at full operation. This filtering engine is based on non-deterministic finite automata (NFAs), efficiently implemented using state transition elements (STEs), allowing us to trace events at a cache-line granularity. Moreover we can change the filters in less than a second, without reprogramming the FPGA or interfering with the running application. This data enables not only debugging the implementation of the interconnect itself, but analyzing the behavior of accelerated applications.
We examine the mathematical basis for using NFAs and describe their implementation on a real coherent CPU-FPGA research platform. We then evaluate the scalability of Dryas for various size NFAs, followed by two different use cases: debugging FPGA implementation of the interconnect and analyzing cache behavior.
toXiv_bot_toot

@tiotasram@kolektiva.social
2026-09-15 07:31:34
Content warning: Short story; cozy-ish science fiction?

Wish inspiration hadn't struck right at 1 a.m. when I have to teach tomorrow, but we'll see if I can get back to sleep now that I'm done with a draft of this story. Glad to have my first entry in my "incredulous young historians of the future" series actually written instead of just imagined. There are surely some typos ahead...
#SciFi #Writing #Technology #ShortStory
"The Age of Progress", a short story by Tiota Sram.
"Your assignment", said the teacher, "is to describe why the progressive vision of technology that gives us the name 'Age of Progress' today failed, and why it was actually a pessimistic view of technology. Your study guides have links to a few sources, but as usual you should synthesize information from at least two knowledge systems, and one of those shouldn't be family-based."
"Ugh", said Ye'xik, "this is gonna be tricky. Wasn't the whole problem with the Age of Progress that they were too optimistic about technology?"
"Well, they did talk a lot about the end of the world and extinction, and I did almost happen, right?" said Finan.
"Yeah, that's gotta count as pessimism, doesn't it?" Gedi chimed in.
"Well..." said Hallavia, with their usual deliberate tone, "I think it's not that simple, or at least it doesn't have to be."
The four of them were walking outside to have lunch, pondering the new assignment from this cycle's history and culture teacher. A brief silence fell as they pondered the Age of Progress.
"Maybe we should look at it through another history system?" offered Finan. "I mean, we've been learning about knowledge systems and lenses, and the 'Ages' lens of just one perspective with its own distortions, right?"
"My mab is working with my omeh on an oral history right now", said Gedi, "maybe I can use that as my second knowledge system? I'll see what they have to say about it!"
"We shouldn't all use the same knowledge systems though", said Ye'xik. "I think there's a bit of a thesis/antithesis thing going on here too? Like we were learning in ideas class?"
"Wait, I missed ideas last week", said Gedi, what's an antithesis?"
"It's just an opposite, really", said Ye'xik. "You take the thesis statement and construct any statement that contradicts it. The two form a pair, and then you can try to find a synthesis that combines both ideas."
"I didn't really get that part", Finan interrupted, "like, if they're contradictory, how could they be expressed together? Wouldn't you need to pick one that's true?... wait I guess maybe if you mixed different knowledge systems? But then would they really be contradictory?"
The group fell silent for a moment in thought.
Hallavi spoke up: "Incommensurate isn't the same as contradictory, I think. That's what it would be if you had two truths from different knowledge systems that didn't fit. Plus... not all knowledge systems have a concept of truth, or of contradiction?"
The group pondered this for a bit more.
"I think maybe there's lots of ways to be contradictory, even in a very logic-hungry knowledge system", said Gedi. "Then if your thesis and antithesis contradict in one way, you could find another sort out 'axis' in which they don't, and state your synthesis from there?"
"Oh, that makes sense", said Ye'xik.
"Anyways what were you saying about the Age of Progress, Ye'xik?" said Gedi.
"Wait", interrupted Hallavi, "Did that mashes sense to you, Finan?"
Finan had been silent, looking down at their feet, but replied "Oh yeah, thanks for checking Hallavi! I think I got the part about synthesis now, thanks Gedi. I was just thinking about optimism and pessimism more. Is that where you were going with this, Ye'xik?"
"Haha, yeah Finan, you got it", said Ye'xik. "Since optimism and pessimism can be opposites, does the teacher actually want us to form a synthesis of them?"
"Oh..." muttered Gedi, "that's a good idea."
"I think..." began Hallavi, pausing to collect their thoughts, "I think the teacher would have told us that, though. Obviously it's not a wrong way to approach this assignment because it incorporates pessimism, but teachers usually aren't too tricky. I think it's okay to be literal about the pessimism thing. And I think I have an idea..."
When Hallavi remained silent for a moment, Ye'xik opened their mouth to speak, but then looked at Hallavi and closed it again. Finan and Gedi were looking at Hallavi too. They pushed through the doors out to the meadow, and settled in their usual place to sit, pulling lunches out of their bags. Hallavi finally spoke up while the others were chewing: "The Age of Progress lasted from the Enlightenment to the Dim Times, and they believed that technology would always get better, no matter what. That's the progressive vision of technology our teacher was talking about. They thought it could solve any problem, and they wouldn't have to worry about weapons or extinctions or the climate or pollution or any of that stuff, because technology would eventually come up with a solution. They looked at the technology that solved problems like diseases or overcame engineering challenges and extrapolated too broadly, basically. That's the idea they had?"
The other three were all nodding their heads, knowing Hallavi needed room to think and put words together.
Hallavi continued: "So it seems like it's optimistic, because they thought it could do anything. But they were thinking about technology like I just talked about it: like an 'it' that could 'do'. That's not what we've been learning in our technology class. Invention is a social phenomenon, and technologies have both material and social bases, not to mention communities of practice and knowledge maintenance. So I think the idea of technological progress divorced from social participation is pessimistic, because it mythologizes technology in a way that makes it seem uncontrollable."
"Huh" said Gedi and Finan while at the same time Ye'xik said "mhmm".
Hallavi looked up shyly at the rest of them, but they were all looking back with admiration.
"I think you're right, Hallavi", said Ye'xik. "Or at least, that's probably what the teacher wanted us to puzzle out. Good thing they asked us to include two knowledge systems so we can each have our own perspectives to contribute, otherwise you'd go first and our presentations would all just be 'What Hallavi said'".
Hallavi blushed but Finan laughed "Hah! You're right and that Ye'xik."
Gedi was looking at their sandwich with some intensity. They looked at Hallavi then back at their sandwich. "It's like they thought they were strapped to an out-of-control rocket, when you put it that way", they said. "It must have been scary, really, to believe that technology was almost an entity, changing in an inevitable way. That word 'inevitable' really takes all the human agency out of it, doesn't it. And even though they kept saying that technology would inevitably solve problems, look at what the technologies they invented actually did!"
Finan shuddered. He added, "Really, it was their dominators who were saying it was inevitable wasn't it? Back then it wasn't like today where historians travel and sample all kinds of ideas, so the primary sources we're reading are almost all from dominators, right?"
Ye'xik responded "Yeah, I keep forgetting to account for that. It was such a weird and horrible time, it's kinda hard to believe everything we read and hear sometimes."
Gedi picked up the thread again "That makes it worse, right? All those dominators saying the stuff they're doing is inevitable, and lying to everyone's faces about it being progress and wonderful stuff, meanwhile two thirds of it is the most awful stuff there's ever been, I mean they could have literally killed everyone and ruined the whole planet, and they almost did."
"They did actually crush a lot of cultures beyond recognition so the survivors had to rebuild with only weak ties to their old traditions", said Hallavi with a quiet intensity.
They all were silent for a moment, pondering the horrors of a bygone age.
Finan broke the silence: "That's a terrible kind of pessimism, to believe that technologcal 'progress' is inevitable, at a time when most people are dominators somewhere in a hierarchy and the ones on top constantly talk about how technologies like medicines will 'save' the world while mostly inventing new technologies of violence. Everyone must have understood what they really meant based on the technologies they were actually developing and investing into. I think I still don't understand how the Age of Progress and the Dim Times could even happen".
"Yeah, and the pessimism is only part of our assignment", signed Ye'xik. "We still have to describe why the progressive vision failed, although I think maybe you just did a lot of that, Finan".
A gloom descended briefly, until Gedi said "Well, this assignment is supposed to take a week or two, right? Thanks to Hallavi we've already cracked the crux, I think, so we don't need to ruminate too much right this moment about ancient history, and we know things turned out okay in the end. Let's finish lunch and go climb a tree!"