Alberto Bartoli - Blog

A few hours ago I have read a masterpiece about the current state of "Cybersecurity and AI", written by an extremely competent person (Marcus Hutchins, the guy that stopped WannaCry ). It is a relatively long essay but I really encourage everyone with some interest in these topics to read it. Not only for the credibility of Hutchins, the breadth and the strength of his arguments, but also for the clarity and sharpness of his writing. The time spent for reading this essay is an excellent investment. I will make it mandatory reading for the students of my Cybersecurity course . Full essay: Machine speed is a lie: stop fighting AI with AI . A few paragraphs that I extracted: Working Notes: Cybersecurity and AI . I must add that I am happy to see that Hutchins makes several points that I emphasize a lot in my course, including: the practical inevitability of initial access and the need to take an "assume breach" standpoint; the necessity of detection and of structural d...

Sto preparando il corso " Principi di IA per l'Ingegneria " che dal prossimo a.a. terrò al primo anno di tutte le lauree triennali in Ingegneria. Molto introduttivo, solo 4 seminari di 2 ore ognuno. Sto anche selezionando qualche link di approfondimento per gli interessati. Un tema molto importante è quello delle cosiddette " hallucinations ": affermazioni generate dalla cosiddetta AI che non hanno alcun legame con la realtà. Fenomeno intrinseco alla tecnologia alla base della cosiddetta AI e molto pericoloso per ovvi motivi. Ho avuto una esperienza personale di hallucination che ho deciso di condividere perché mi pare molto, molto istruttiva.  Mio padre è deceduto nel 1972. Amava scrivere e dipengere, per passione personale. I contenuti su di lui su Internet sono ovviamente pochissimi: solo un piccolissimo sito web creato da me. Il sito web contiene link ad alcuni suoi racconti e ad un libro che aveva scritto sulla storia del paese in cui vivevamo, Peccioli. ...

 An excerpt from a blog post by one of the maintainers of curl . A person with a lot of "real world experience" on one of the most widely used software tools in the planet. Everything in the bulleted list below has been just copied-and-pasted (bold is mine, it was not in the original post). I have not added any comment, it is not necessary. This analysis goes in exactly the same direction that I hypothesized in my previous posts ( here and here ). Before this first Mythos report, we had already scanned curl with several different very capable AI powered tools (I mean in addition to running a number of “normal” static code analyzers all the time, using the pickiest compiler options and doing fuzzing on it for years etc)... These tools and the analyses they have done have triggered somewhere between two and three hundred bugfixes merged in curl through-out the recent 8-10 months or so. A bunch of the findings these AI tools reported were confirmed vulnerabilities and have b...

 Questa volta in italiano. Ogni tanto vedo notizie strettamente collegate ad argomenti di cui ho parlato a lezione pochissimi giorni prima ( esempio ). Ieri sera ne ho visto una molto interessante, legata proprio alla lezione di Cybersecurity di ieri mattina. La lezione era la prima sull'argomento "Memory corruption". Tra le varie cose, ho detto che: Non tutti gli errori ("bug") sono vulnerabilità ; non tutte le vulnerabilità sono sfruttabili ( exploitable ). L' impatto di una vulnerabilità dipende non tanto dall'errore ma dal programma in cui è stato commesso l'errore. Tale dipendenza è estremamente complessa e pressoché impossibile da prevedere in generale. Uno stesso errore in programmi diversi può non avere alcun impatto di sicurezza, avere impatto marginale, avere impatto potenzialmente catastrofico. Le stesse considerazioni valgono per la possibilità di sfruttare una vulnerabilità conseguente ad una particolare tipologia di errore: può essere ...

UPDATE AT THE END I am playing with Gemini for extracting MITRE ATT&CK techniques from cybersecurity incident reports automatically (MITRE ATT&CK is a powerful framework for reasoning about attacks and I use this framework intensively in my Cybersecurity course ): you give Gemini the URL of a report and will immediately obtain the attack techniques used in that attack campaign. Here a spreadsheet with some of the outputs. This usage of "the AI" is potentially very useful for grasping the essentials of an attack campaign quickly and providing students with concrete examples. It is also an usage that fits an essential but often overlooked requirements of AI applications: the cost of a mistake must be small . The prompt I give to Gemini actually asks to extract another important piece of information: the vulnerabilities possibly used in that campaign. In my early attempts I asked Gemini to tell, for each listed vulnerability, whether it was still unknown to software...

A follow-up to my previous post on Mythos Preview. The AI Security Institute (AISI) has published a very interesting analysis of Mythos Preview . Very interesting because: AISI is " a mission-driven research organisation in the heart of the UK government ". Its reports are clearly much more credible than claims of the form " our last product is too strong to give you, believe us " by a private US company, that is currently losing lot of money, that is fiercely battling against other  companies in the AI arena, that is extremely good at fuelling hype about their products and capabilities. They consider complete cybersecurity tasks, i.e. CTF (capture the flag) competitions and attacks to a simulated organization. They compare the behavior of different models for a given "token budget". Not surprisingly, Mythos Preview is indeed very good and better than previous models, but it is definitely not the coming Apocalipsis. In particular, it is the first tool th...